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

    Neuronpedia

    INDEX
    Explanations

    references to specific technical terms related to digital technologies or web development

    oai_token-act-pair · gpt-3.5-turbo

    identifiers or codes related to technical specifications or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ously
    -1.06
     Yor
    -0.79
    onymous
    -0.79
    furt
    -0.76
     Rite
    -0.76
    atively
    -0.72
    ous
    -0.72
    ative
    -0.70
    ature
    -0.70
    ocene
    -0.69
    POSITIVE LOGITS
    heed
    0.84
    rack
    0.80
    ree
    0.80
    arlane
    0.79
    ritch
    0.74
    rush
    0.66
    anya
    0.65
    Ultra
    0.64
     Kut
    0.64
    restrial
    0.64
    Act Density 0.095%

    No Known Activations