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

    Neuronpedia

    INDEX
    Explanations

    words related to criticism and disapproval

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "call" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orgetown
    -0.78
     guiActiveUn
    -0.78
     ende
    -0.75
    lings
    -0.71
    llers
    -0.70
    Journal
    -0.67
    leness
    -0.67
    lyak
    -0.67
    ©¶æ
    -0.66
    eah
    -0.65
    POSITIVE LOGITS
    axy
    0.89
    ength
    0.82
    ogue
    0.77
    iard
    0.76
    asper
    0.76
     Spears
    0.74
    sbm
    0.72
     999
    0.68
    enged
    0.68
    aries
    0.66
    Act Density 0.042%

    No Known Activations