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

    Neuronpedia

    INDEX
    Explanations

    phrases related to constructing or assembling something, particularly in a setting involving imitation or approximation

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases related to deception or trickery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unfocusedRange
    -0.81
    ourses
    -0.79
    clerosis
    -0.76
     GOODMAN
    -0.76
    ibel
    -0.72
     actionGroup
    -0.72
     RELEASE
    -0.70
    ourse
    -0.70
    IRC
    -0.69
    uve
    -0.68
    POSITIVE LOGITS
    wra
    0.72
     Hats
    0.68
    balls
    0.68
     caric
    0.67
    pas
    0.65
    pants
    0.64
     excuse
    0.63
     hide
    0.62
     whisk
    0.62
    boot
    0.61
    Act Density 0.215%

    No Known Activations