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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the release or distribution of products or information

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" followed by various forms of articles and pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiveness
    -0.74
    reprene
    -0.70
    unin
    -0.69
    eor
    -0.69
    oller
    -0.68
    ajor
    -0.67
    erest
    -0.66
    ancy
    -0.65
    owell
    -0.63
    osc
    -0.63
    POSITIVE LOGITS
     follows
    1.14
    phy
    1.05
    ynchron
    0.98
    part
    0.96
    pires
    0.92
     well
    0.91
     opposed
    0.88
    bestos
    0.86
     soon
    0.86
    pired
    0.86
    Act Density 0.209%

    No Known Activations