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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating belief or conviction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.17
    uell
    -0.16
    quel
    -0.15
    yny
    -0.15
    lal
    -0.15
    iere
    -0.15
    filer
    -0.14
    wich
    -0.14
    ercul
    -0.14
    ega
    -0.14
    POSITIVE LOGITS
    fulness
    0.15
    worth
    0.15
    fully
    0.15
    lessly
    0.15
    618
    0.15
    اÙĨس
    0.15
    -bel
    0.15
    ROUP
    0.14
    ances
    0.14
    608
    0.14
    Act Density 0.052%

    No Known Activations