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

    Neuronpedia

    INDEX
    Explanations

    words that express emotional states or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     relent
    -0.07
    ãģıãĤĭ
    -0.06
    bote
    -0.06
    rait
    -0.06
    ãģķãĤĮãĤĭ
    -0.06
    lanır
    -0.06
     explan
    -0.06
     undergo
    -0.06
    #=
    -0.06
    nett
    -0.06
    POSITIVE LOGITS
     been
    0.19
     Been
    0.17
    been
    0.16
    Been
    0.16
     BEEN
    0.14
     telah
    0.13
     hasn
    0.13
     haven
    0.12
    've
    0.12
    ’ve
    0.11
    Act Density 0.192%

    No Known Activations