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

    Neuronpedia

    INDEX
    Explanations

    language related to blame and interpersonal conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.20
    ullo
    -0.17
    ">//
    -0.16
    abler
    -0.15
    assignments
    -0.15
    LARI
    -0.15
    lisi
    -0.15
    =\"/
    -0.15
     pornost
    -0.15
    /lg
    -0.15
    POSITIVE LOGITS
    elt
    0.18
    inh
    0.14
     Booker
    0.14
     —
    0.14
    w
    0.13
     Bias
    0.13
     baja
    0.13
     sink
    0.13
    vester
    0.13
    bet
    0.13
    Act Density 0.301%

    No Known Activations