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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "hang" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.61
    queryInterface
    -0.57
    ɵɵ
    -0.54
     Inno
    -0.54
    __;
    -0.53
    -0.53
    anol
    -0.52
     breath
    -0.52
    zzleHttp
    -0.52
     scan
    -0.51
    POSITIVE LOGITS
     colgantes
    0.73
     ainfi
    0.69
     desmotivaciones
    0.68
     gereja
    0.67
     Moscú
    0.65
     zijne
    0.63
     Italij
    0.62
     ſeveral
    0.61
     poffible
    0.61
     étoient
    0.60
    Act Density 0.252%

    No Known Activations