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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating two or more entities or concepts being mentioned together

    oai_token-act-pair · gpt-3.5-turbo

    the word "along" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.83
    ptive
    -0.72
    nas
    -0.70
    orius
    -0.70
    ns
    -0.69
    auri
    -0.66
    ulas
    -0.66
    BLE
    -0.66
    agara
    -0.64
    onomy
    -0.64
    POSITIVE LOGITS
    side
    0.79
    wagon
    0.77
    along
    0.74
    rafted
    0.67
     Vest
    0.66
    idth
    0.66
    semble
    0.64
    wikipedia
    0.64
     wagon
    0.63
    axter
    0.62
    Act Density 0.018%

    No Known Activations