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

    Neuronpedia

    INDEX
    Explanations

    references to friendships and close personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otch
    -0.18
    eldig
    -0.17
    GRID
    -0.15
    phet
    -0.15
    ãĥ³ãĥIJãĥ¼
    -0.15
    ental
    -0.15
    é»
    -0.15
    sher
    -0.15
    bus
    -0.14
    aux
    -0.14
    POSITIVE LOGITS
     organ
    0.17
    dds
    0.14
    aho
    0.14
    ÂĽ
    0.14
    lier
    0.14
     Fol
    0.14
     SES
    0.14
    ylon
    0.13
    μμε
    0.13
    lfw
    0.13
    Act Density 0.065%

    No Known Activations