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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong beliefs or convictions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of belief or conviction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nec
    -0.76
    apeake
    -0.75
    yna
    -0.73
    nice
    -0.69
    cue
    -0.66
    ack
    -0.66
    clud
    -0.64
    effect
    -0.64
    hoff
    -0.62
    eding
    -0.62
    POSITIVE LOGITS
     passionately
    1.01
     strongly
    0.85
    phas
    0.84
    ieves
    0.74
    ieve
    0.71
     that
    0.70
     firmly
    0.68
    lessly
    0.67
    ievers
    0.66
    fully
    0.65
    Act Density 0.069%

    No Known Activations