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

    Neuronpedia

    INDEX
    Explanations

    words related to fitting or compatibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words related to fitting or compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¼
    -0.63
    afa
    -0.61
     reserve
    -0.58
    cipl
    -0.58
    introdu
    -0.58
    ledge
    -0.58
    ijk
    -0.57
     laun
    -0.57
    deg
    -0.57
    yard
    -0.55
    POSITIVE LOGITS
     fits
    1.20
     fit
    1.06
    fits
    1.06
     snug
    0.97
    terness
    0.94
     fitting
    0.82
    fit
    0.80
    encies
    0.77
    rss
    0.76
    Fit
    0.75
    Act Density 0.006%

    No Known Activations