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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing something positively

    oai_token-act-pair · gpt-3.5-turbo

    the word "nice" and its variations or contexts that imply positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogens
    -0.74
    onics
    -0.73
    rules
    -0.72
    uilding
    -0.71
    orders
    -0.70
    authorized
    -0.70
    ationally
    -0.69
    reports
    -0.68
    ivals
    -0.66
    bin
    -0.66
    POSITIVE LOGITS
     touch
    0.99
     touches
    0.97
     sounding
    0.89
     neat
    0.88
     little
    0.87
     nice
    0.83
     gesture
    0.83
     smelling
    0.82
     warm
    0.82
     fluffy
    0.80
    Act Density 0.055%

    No Known Activations