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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-esteem and confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alse
    -0.07
    icer
    -0.07
    reta
    -0.07
    ward
    -0.07
    oldt
    -0.07
    uden
    -0.07
    oler
    -0.07
    uns
    -0.06
    exus
    -0.06
    rio
    -0.06
    POSITIVE LOGITS
    /conf
    0.08
    plib
    0.08
    /self
    0.07
    -confidence
    0.07
     confidence
    0.07
    confidence
    0.07
     levels
    0.07
    anggal
    0.07
    andır
    0.06
    ÑĢаÑĩ
    0.06
    Act Density 0.006%

    No Known Activations