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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to requirements or obligations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to requirements or prerequisites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arer
    -0.84
    Äį
    -0.77
    oche
    -0.76
    acus
    -0.74
    jad
    -0.74
    entimes
    -0.74
    ateurs
    -0.73
    ared
    -0.72
    arthed
    -0.71
    peak
    -0.69
    POSITIVE LOGITS
     portion
    0.93
     sections
    0.92
     amount
    0.91
     timeframe
    0.90
     paperwork
    0.89
     technical
    0.85
     permissions
    0.84
     portions
    0.81
     section
    0.81
     parts
    0.80
    Act Density 0.088%

    No Known Activations