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

    Neuronpedia

    INDEX
    Explanations

    facts or statements about specific topics related to laws, health, and events

    oai_token-act-pair · gpt-3.5-turbo

    statements about the status or condition of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     viz
    -0.69
    âĶĢâĶĢâĶĢâĶĢ
    -0.60
    âĶĢâĶĢ
    -0.59
     originals
    -0.59
     thereof
    -0.59
     Hundred
    -0.59
     stands
    -0.58
     Till
    -0.57
     sidx
    -0.57
     totality
    -0.57
    POSITIVE LOGITS
    senal
    0.94
     indeed
    0.93
     abound
    0.85
     also
    0.84
    rael
    0.80
     generally
    0.80
     prolifer
    0.80
     typically
    0.76
     understandably
    0.76
    omorph
    0.75
    Act Density 0.562%

    No Known Activations