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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate reluctance or negative outcomes in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     paljon
    -0.50
    principalTable
    -0.48
     much
    -0.47
    もう少し
    -0.47
    很好的
    -0.46
    usaha
    -0.46
     stava
    -0.46
    Same
    -0.45
     frecuentes
    -0.45
     túnel
    -0.45
    POSITIVE LOGITS
     تضيفلها
    0.82
     Signalez
    0.75
    ValueStyle
    0.75
    tagHelperRunner
    0.71
    Lá
    0.68
     وتسجيلات
    0.68
     jamais
    0.67
    ngOnInit
    0.67
    ništ
    0.67
    aarrggbb
    0.66
    Act Density 0.048%

    No Known Activations