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

    Neuronpedia

    INDEX
    Explanations

    instances of reassurance or encouragement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating continuity or persistent presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    buster
    -0.86
    strip
    -0.71
    plug
    -0.64
    breaker
    -0.63
    gypt
    -0.60
    antis
    -0.59
    breakers
    -0.59
    issance
    -0.58
    Mesh
    -0.56
     bombed
    -0.56
    POSITIVE LOGITS
     plenty
    0.92
     lots
    0.79
     differences
    0.76
     LOT
    0.75
     ample
    0.72
     overlap
    0.72
    thora
    0.71
     unanim
    0.71
    umerous
    0.71
     occasions
    0.67
    Act Density 0.137%

    No Known Activations