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

    Neuronpedia

    INDEX
    Explanations

    words related to gradual processes or steps in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gradual processes or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     XXX
    -0.83
    rup
    -0.83
     Aval
    -0.79
     Scene
    -0.78
     CLIENT
    -0.73
    eers
    -0.67
    XY
    -0.67
     Country
    -0.66
    ents
    -0.65
     PAC
    -0.65
    POSITIVE LOGITS
     phased
    1.21
    ftime
    0.91
    etheless
    0.90
     staggered
    0.89
    areth
    0.85
    odge
    0.80
    cone
    0.80
    cence
    0.77
    ither
    0.77
    igree
    0.75
    Act Density 0.031%

    No Known Activations