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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating disappointment or changes in personal circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /fw
    -0.16
     buflen
    -0.14
    ondo
    -0.14
    /generated
    -0.14
    unga
    -0.13
    jerne
    -0.13
    /aws
    -0.13
    ?a
    -0.13
    ------+------+
    -0.13
    lund
    -0.13
    POSITIVE LOGITS
    caster
    0.17
     vs
    0.15
    icho
    0.14
    alice
    0.14
     Norton
    0.13
    ä¹
    0.13
    vangst
    0.13
    اÙĩÙħ
    0.13
    .Standard
    0.13
    ville
    0.13
    Act Density 0.104%

    No Known Activations