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

    Neuronpedia

    INDEX
    Explanations

    university-related events and references

    oai_token-act-pair · gpt-3.5-turbo

    references to academic institutions and specific political issues or controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abase
    -0.65
    ij士
    -0.62
    ificant
    -0.57
     seiz
    -0.56
    theless
    -0.56
    forth
    -0.56
     divided
    -0.55
     Wem
    -0.54
    GROUP
    -0.53
    izontal
    -0.53
    POSITIVE LOGITS
    .</
    0.81
    !".
    0.71
    '.
    0.71
    ".
    0.71
    ?".
    0.70
    .[
    0.70
    .?
    0.70
     etc
    0.68
    $.
    0.68
    *.
    0.67
    Act Density 0.736%

    No Known Activations