Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant changes or transitions in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    something ending or stopping

    np_acts-logits-general · gemini-2.0-flash

    ending of organizations or positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Réponses
    -0.79
    HtmlAttribute
    -0.67
    numerusform
    -0.62
    sizeCache
    -0.61
    SBATCH
    -0.59
    __*/
    -0.58
    makeConstraints
    -0.58
    endpush
    -0.55
    AccessorTable
    -0.55
     חיצוניים
    -0.55
    POSITIVE LOGITS
     leaving
    0.84
     uncer
    0.83
     permanently
    0.81
     навсегда
    0.79
     laissant
    0.78
     abruptly
    0.76
    leaving
    0.75
     définitivement
    0.74
     forever
    0.73
    Portail
    0.72
    Act Density 0.455%

    No Known Activations