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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of unwillingness or incapacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĶ
    -0.15
    iaux
    -0.14
    _asm
    -0.14
    νοÏĤ
    -0.14
    sta
    -0.14
    dete
    -0.14
    cht
    -0.14
    ÌĨ
    -0.14
    лами
    -0.14
    halt
    -0.13
    POSITIVE LOGITS
     want
    0.25
     wants
    0.21
     confidence
    0.20
     wanted
    0.19
     feel
    0.19
     muá»ijn
    0.19
     mood
    0.18
     trust
    0.18
     Mood
    0.17
    Want
    0.17
    Act Density 0.086%

    No Known Activations