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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location or time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.91
     iſt
    -0.83
     ――――――――
    -0.79
    jména
    -0.78
     itſelf
    -0.77
     ་་
    -0.77
     Anſ
    -0.77
     pleaſure
    -0.76
     Hadrian
    -0.76
     auffi
    -0.75
    POSITIVE LOGITS
    Σε
    0.82
     at
    0.81
    På
    0.78
     na
    0.78
     σε
    0.75
     på
    0.74
    νονται
    0.72
    WithFormat
    0.71
     en
    0.69
    efully
    0.69
    Act Density 0.011%

    No Known Activations