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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acad
    -0.07
    578
    -0.06
     oneself
    -0.06
    oly
    -0.06
    borg
    -0.06
    fo
    -0.06
     ->
    -0.05
     Gat
    -0.05
    ing
    -0.05
     reportedly
    -0.05
    POSITIVE LOGITS
    bung
    0.08
    raith
    0.07
    assin
    0.07
    elters
    0.07
    iegel
    0.07
    ustain
    0.07
    .Alpha
    0.07
     Ñıв
    0.07
    _defs
    0.07
    onds
    0.07
    Act Density 0.026%

    No Known Activations