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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to decision-making and selection criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bite
    -0.15
    oral
    -0.14
    ãģıãģł
    -0.14
    REATE
    -0.14
    dom
    -0.14
    atre
    -0.14
     Kou
    -0.14
    .Lines
    -0.14
    åĸ
    -0.14
    ato
    -0.13
    POSITIVE LOGITS
    ubu
    0.19
    hurst
    0.16
    rij
    0.15
     Slack
    0.14
    fds
    0.14
    ाà¤Ń
    0.14
    xBB
    0.14
    ubbo
    0.14
     weighting
    0.14
    ansom
    0.14
    Act Density 0.386%

    No Known Activations