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

    Neuronpedia

    INDEX
    Explanations

    patterns of refusal or denial relating to decision-making or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    crm
    -0.15
    riba
    -0.15
    apur
    -0.15
    uppe
    -0.15
    mrt
    -0.14
    ãĤ¸ãĤ¢
    -0.14
    lexport
    -0.14
    mutable
    -0.14
    xbf
    -0.14
    ardy
    -0.13
    POSITIVE LOGITS
     accept
    0.30
     accepting
    0.28
    accept
    0.28
     accepts
    0.28
     Accept
    0.26
     let
    0.24
    Accept
    0.24
     allow
    0.23
     letting
    0.23
     ACCEPT
    0.23
    Act Density 0.099%

    No Known Activations