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

    Neuronpedia

    INDEX
    Explanations

    quotes or reported speech

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements or expressions of intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.70
    soDeliveryDate
    -0.67
    visors
    -0.67
    MpServer
    -0.66
    ================================================================
    -0.66
    Assembly
    -0.65
    imi
    -0.65
    acher
    -0.64
    Stretch
    -0.63
    Ŀ
    -0.62
    POSITIVE LOGITS
     instantly
    1.07
     automatically
    0.94
     suddenly
    0.91
     magically
    0.89
     invariably
    0.89
     immediately
    0.88
     inevitably
    0.79
     unconsciously
    0.79
     subtract
    0.78
     invol
    0.76
    Act Density 0.621%

    No Known Activations