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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing positive emotions and sentiments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positive emotions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     watershed
    -0.71
    ibaba
    -0.71
    è¯
    -0.71
    NESS
    -0.69
    soDeliveryDate
    -0.64
     containment
    -0.61
    ths
    -0.61
    ailability
    -0.61
    atomic
    -0.60
     teasp
    -0.59
    POSITIVE LOGITS
    enance
    0.80
    ttes
    0.70
    ovan
    0.67
    poke
    0.65
    ophob
    0.65
    _>
    0.65
    yles
    0.64
    agos
    0.63
    uate
    0.59
    lled
    0.59
    Act Density 0.189%

    No Known Activations