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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and internal character thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    нгред
    -0.67
    pecabe
    -0.62
    bibfield
    -0.61
    Bakgrunnsstoff
    -0.60
     increí
    -0.60
    الإنجليزية
    -0.60
    majánló
    -0.59
     raiſ
    -0.58
    +#+
    -0.58
    ロウィン
    -0.58
    POSITIVE LOGITS
     thought
    0.42
    '),
    0.41
     gedachten
    0.38
     pensamientos
    0.36
    '){
    0.34
     thinking
    0.33
    ']);
    0.33
    ()){
    0.32
    HasColumnType
    0.31
    ){
    0.30
    Act Density 0.213%

    No Known Activations