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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or proper nouns, particularly surnames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alars
    -0.18
    rita
    -0.16
    å°½
    -0.15
    antas
    -0.15
    lander
    -0.15
    ستاÙĨ
    -0.15
    .strict
    -0.15
    hus
    -0.14
    landers
    -0.14
    buster
    -0.14
    POSITIVE LOGITS
    NAL
    0.16
    cline
    0.15
    yte
    0.15
     undercut
    0.15
    NL
    0.15
    y
    0.14
    intl
    0.14
    наÑĩе
    0.14
     Loren
    0.14
    URES
    0.13
    Act Density 0.028%

    No Known Activations