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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating a negative preference or avoidance

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing a desire or reluctance regarding a specific action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.81
    ework
    -0.74
    bard
    -0.70
    hiba
    -0.70
    soDeliveryDate
    -0.69
     Enhancement
    -0.69
    metadata
    -0.68
    VERTISEMENT
    -0.67
    icol
    -0.67
    strength
    -0.67
    POSITIVE LOGITS
     anymore
    0.93
     anybody
    0.91
     anyone
    0.85
     anything
    0.85
    reprene
    0.83
     nor
    0.80
     any
    0.77
    ANY
    0.76
     necessarily
    0.75
     surprises
    0.73
    Act Density 0.041%

    No Known Activations