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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives or superlatives

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives expressing positive or negative evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾į
    -0.82
    çīĪ
    -0.81
    ymes
    -0.81
    dinand
    -0.80
    ãĥīãĥ©
    -0.80
    appings
    -0.79
    èĪ
    -0.79
    ittees
    -0.75
    ilings
    -0.74
    İĭ
    -0.73
    POSITIVE LOGITS
     thing
    1.43
     imaginable
    1.10
     conceivable
    0.93
     EVER
    0.91
     ever
    0.89
     aspect
    0.88
     way
    0.85
     Thing
    0.84
    thing
    0.84
     possible
    0.82
    Act Density 0.159%

    No Known Activations