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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الحره
    -0.51
     zape
    -0.38
     senare
    -0.37
     kteří
    -0.36
    fvar
    -0.36
     ktorí
    -0.36
    bitField
    -0.35
     Lots
    -0.35
    CppCodeGen
    -0.35
     lots
    -0.34
    POSITIVE LOGITS
     interested
    0.77
     sure
    0.72
    interested
    0.60
    setupUi
    0.58
     inclined
    0.57
     afraid
    0.57
     INTEREST
    0.57
     ashamed
    0.55
     privy
    0.54
     allowed
    0.53
    Act Density 0.173%

    No Known Activations