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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and prepositions commonly used in writing

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and connecting phrases in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emen
    -0.72
    .
    -0.70
    .�
    -0.69
    .).
    -0.68
    .[
    -0.66
    .''
    -0.65
    .:
    -0.64
    .]
    -0.63
     ."
    -0.63
    _.
    -0.63
    POSITIVE LOGITS
    oubted
    0.61
    rogens
    0.60
     unable
    0.60
     assuming
    0.60
    acles
    0.58
    ilings
    0.58
    headers
    0.56
    ancock
    0.56
    withstanding
    0.56
    ilater
    0.55
    Act Density 0.403%

    No Known Activations