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

    Neuronpedia

    INDEX
    Explanations

    instances that signify irony or unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.57
    ArgsConstructor
    -0.57
     OGS
    -0.57
    thâu
    -0.56
    PerformLayout
    -0.56
    новниш
    -0.54
     Marius
    -0.53
     Himo
    -0.52
     parms
    -0.52
     intensities
    -0.51
    POSITIVE LOGITS
     Ironically
    0.68
     ironically
    0.65
    brigens
    0.63
    xically
    0.59
     fact
    0.59
    Interestingly
    0.58
     faktisk
    0.57
    何と
    0.57
    なんと
    0.56
    Кстати
    0.56
    Act Density 0.247%

    No Known Activations