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

    Neuronpedia

    INDEX
    Explanations

    dialogue and interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enthal
    -0.15
    ñana
    -0.15
    иÑģлов
    -0.14
    rava
    -0.14
    uegos
    -0.14
     LOVE
    -0.14
    .sax
    -0.14
    çe
    -0.13
    adele
    -0.13
    izzard
    -0.13
    POSITIVE LOGITS
     worry
    0.52
     concern
    0.48
     concerns
    0.48
     worries
    0.46
     wonder
    0.46
     Concern
    0.44
     worried
    0.43
     worrying
    0.41
     concerned
    0.39
    Concern
    0.39
    Act Density 0.088%

    No Known Activations