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

    Neuronpedia

    INDEX
    Explanations

    words related to self-assurance and belief in one's abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.91
     intptr
    -0.81
     ModelRenderer
    -0.79
    AnchorStyles
    -0.75
     ModelExpression
    -0.75
     Roskov
    -0.69
     ExecuteAsync
    -0.66
    Portail
    -0.65
     ligiloj
    -0.64
    addContainerGap
    -0.63
    POSITIVE LOGITS
     confidence
    1.49
     Confidence
    1.31
    confidence
    1.29
    Confidence
    1.25
     confident
    0.99
     hesitate
    0.92
     hesitation
    0.85
     faith
    0.83
     hesitant
    0.82
     confidently
    0.76
    Act Density 0.099%

    No Known Activations