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

    Neuronpedia

    INDEX
    Explanations

    the presence of whitespace or gaps in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </blockquote>
    -0.70
    <i>
    -0.67
    </h6>
    -0.63
    <code>
    -0.62
    </code>
    -0.61
     
    -0.60
    <em>
    -0.59
    </sub>
    -0.57
    </i>
    -0.57
     […]
    -0.53
    POSITIVE LOGITS
     !$
    0.71
     surla
    0.69
    \
    0.68
     \&
    0.67
    expandindo
    0.66
     \%
    0.64
    enumi
    0.62
    StructEnd
    0.61
    \{
    0.61
     \$
    0.61
    Act Density 0.062%

    No Known Activations