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

    Neuronpedia

    INDEX
    Explanations

    themes related to blame and personal accountability in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lea
    -0.16
     Void
    -0.15
    еÐ
    -0.15
    indle
    -0.15
     fi
    -0.15
    bron
    -0.14
    lauf
    -0.14
    enville
    -0.14
    :void
    -0.14
     driv
    -0.14
    POSITIVE LOGITS
    99
    0.20
    icky
    0.18
    ick
    0.16
    unction
    0.15
    éĴŁ
    0.15
    akis
    0.15
    oub
    0.14
    98
    0.14
    100
    0.14
    rupa
    0.14
    Act Density 0.213%

    No Known Activations