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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotion and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oir
    -0.16
    itzer
    -0.15
     sürede
    -0.14
    ErrorException
    -0.14
    Ñĥда
    -0.14
    alles
    -0.14
    esor
    -0.13
    jom
    -0.13
    lassen
    -0.13
    سÙĩ
    -0.13
    POSITIVE LOGITS
     greatly
    0.28
     very
    0.25
     deeply
    0.25
     muito
    0.21
     beyond
    0.20
     bardzo
    0.20
     sehr
    0.20
     mucho
    0.19
    ensely
    0.19
    deep
    0.19
    Act Density 0.208%

    No Known Activations