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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to self-belief and confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    нÑı
    -0.17
    rib
    -0.15
    yy
    -0.15
    yny
    -0.15
    quel
    -0.15
    arakter
    -0.14
    pg
    -0.14
    utz
    -0.14
    stell
    -0.14
    yyy
    -0.14
    POSITIVE LOGITS
    worthy
    0.18
    ance
    0.17
    fulness
    0.16
    enco
    0.15
    bel
    0.15
     Bel
    0.15
     strongly
    0.15
    vably
    0.15
    252
    0.15
    ances
    0.14
    Act Density 0.040%

    No Known Activations