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

    Neuronpedia

    INDEX
    Explanations

    instances of interpersonal relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isher
    -0.15
    738
    -0.15
    apat
    -0.15
    apia
    -0.15
    dz
    -0.14
    permanent
    -0.14
    /op
    -0.14
    izon
    -0.14
    iod
    -0.14
     zel
    -0.14
    POSITIVE LOGITS
    oze
    0.17
    OCK
    0.16
    .WinForms
    0.15
    лаÑĢа
    0.15
    oft
    0.15
     coat
    0.15
    wert
    0.14
     Mant
    0.14
    SAM
    0.14
     forfe
    0.14
    Act Density 0.002%

    No Known Activations