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

    Neuronpedia

    INDEX
    Explanations

    instances of vulgar or offensive language

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.66
    UnusedPrivate
    -0.59
     nahilalakip
    -0.58
     estekak
    -0.57
    providedIn
    -0.57
     TestBed
    -0.56
     préférence
    -0.54
    发表于
    -0.53
    utilisons
    -0.53
    └──
    -0.53
    POSITIVE LOGITS
    ="@+
    0.69
     gratu
    0.65
     profane
    0.58
    setImage
    0.58
     CanadaChoose
    0.56
    娩
    0.56
    \{\\
    0.55
     foul
    0.54
    ɵɵ
    0.54
     obscene
    0.53
    Act Density 0.036%

    No Known Activations