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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global impact and influence

    oai_token-act-pair · gpt-3.5-turbo

    references to global contexts or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.87
    inen
    -0.76
    nis
    -0.73
     istg
    -0.72
    qua
    -0.69
    chron
    -0.63
    nery
    -0.63
    essee
    -0.62
     Tigers
    -0.59
    act
    -0.58
    POSITIVE LOGITS
    clock
    0.86
     corners
    0.84
    perty
    0.77
    eatures
    0.72
    atform
    0.70
    abouts
    0.66
    lasses
    0.65
    tones
    0.61
     midday
    0.60
    andise
    0.60
    Act Density 0.047%

    No Known Activations