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

    Neuronpedia

    INDEX
    Explanations

    versions or revisions mentioned within a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of software versions or revisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aghan
    -0.76
     Berm
    -0.69
    care
    -0.65
     looms
    -0.64
     foul
    -0.64
    affles
    -0.63
    rouse
    -0.63
     accum
    -0.62
     distur
    -0.62
    wage
    -0.59
    POSITIVE LOGITS
     Version
    3.76
    Version
    2.66
     version
    2.18
     VERS
    2.06
     versions
    1.81
    version
    1.79
    VERSION
    1.77
     Vers
    1.51
    Versions
    1.49
    versions
    1.42
    Act Density 0.007%

    No Known Activations