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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve "both" in a context comparing or combining two entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the conjunction "and" along with a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uel
    -0.71
    tec
    -0.69
    elle
    -0.69
    Ļ½
    -0.67
    IJ
    -0.66
    raq
    -0.66
    eks
    -0.66
    irens
    -0.65
    Topics
    -0.65
    ³
    -0.65
    POSITIVE LOGITS
     ours
    0.84
     nons
    0.79
    nam
    0.74
     hers
    0.70
     otherwise
    0.69
    chard
    0.67
     theirs
    0.66
     yours
    0.63
     nonviolent
    0.59
     externally
    0.59
    Act Density 0.119%

    No Known Activations