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

    Neuronpedia

    INDEX
    Explanations

    specific conditions or rules set by authorities that individuals must follow

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving obligations, permissions, and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.59
     Lime
    -0.58
    polit
    -0.57
     transpired
    -0.55
     incorporation
    -0.54
     Satanic
    -0.54
    ital
    -0.54
     Beg
    -0.53
    parse
    -0.53
     Fuck
    -0.52
    POSITIVE LOGITS
     nevertheless
    1.04
     nonetheless
    1.03
    etheless
    0.85
     invariably
    0.83
    Ĥİ
    0.80
     themselves
    0.80
     likewise
    0.79
     promptly
    0.75
     surely
    0.74
    onite
    0.74
    Act Density 0.308%

    No Known Activations