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

    Neuronpedia

    INDEX
    Explanations

    references to research institutions and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to research organizations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icago
    -0.67
    âĶĢâĶĢ
    -0.65
     femin
    -0.63
    size
    -0.62
    EMA
    -0.60
    nea
    -0.60
    anza
    -0.59
    ilage
    -0.57
    conv
    -0.57
     gent
    -0.57
    POSITIVE LOGITS
     Associates
    0.87
     Laboratory
    0.83
     Institute
    0.81
     Laboratories
    0.79
     Scientist
    0.79
    edIn
    0.78
    ateur
    0.76
     assistants
    0.76
    Gate
    0.76
     laboratories
    0.75
    Act Density 0.024%

    No Known Activations