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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or discussions related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ".[
    -0.75
    !.
    -0.69
    ,...
    -0.69
    tek
    -0.67
    !".
    -0.66
     ILCS
    -0.63
     ........
    -0.62
     contrad
    -0.62
    Í
    -0.61
     constitu
    -0.61
    POSITIVE LOGITS
     ado
    0.63
     extends
    0.63
     Lomb
    0.60
    ivalry
    0.58
     Chal
    0.58
    eatures
    0.57
    resents
    0.57
    indal
    0.57
    Lex
    0.56
     Horizon
    0.56
    Act Density 0.398%

    No Known Activations