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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public speaking or presentations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly exclamation points and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Darth
    -0.57
     grav
    -0.53
     *
    -0.51
     Lump
    -0.51
    Alert
    -0.49
     public
    -0.48
     road
    -0.47
     craft
    -0.47
     Tesla
    -0.47
     Ant
    -0.47
    POSITIVE LOGITS
    !,
    2.91
    ?,
    2.60
    !.
    2.09
    /,
    2.07
    $,
    1.82
    *,
    1.68
    !",
    1.68
    ®,
    1.58
    (),
    1.56
    +,
    1.56
    Act Density 0.023%

    No Known Activations