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

    Neuronpedia

    INDEX
    Explanations

    elements that indicate data formatting or structuring in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDD
    -0.16
    ebi
    -0.15
    AFX
    -0.15
    SKIP
    -0.15
     Vert
    -0.15
    êu
    -0.15
    strom
    -0.14
     INCIDENT
    -0.14
    OKIE
    -0.14
    ÙĪاء
    -0.14
    POSITIVE LOGITS
    142
    0.63
    143
    0.62
    140
    0.61
    141
    0.59
    144
    0.58
    146
    0.56
    145
    0.55
    147
    0.55
    148
    0.52
    139
    0.52
    Act Density 0.090%

    No Known Activations