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

    Neuronpedia

    INDEX
    Explanations

    mentions of being under certain situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uria
    -0.76
    iquid
    -0.69
    ubi
    -0.65
    ecided
    -0.65
     outweigh
    -0.64
    pell
    -0.62
     ahead
    -0.62
    behind
    -0.62
     outwe
    -0.60
    ndra
    -0.60
    POSITIVE LOGITS
     guise
    1.15
     ausp
    1.11
     assumption
    0.92
     supervision
    0.88
     circumstances
    0.86
    ãģĨ
    0.85
     microscope
    0.85
    ĵĺ
    0.83
    ħĭ
    0.82
     jurisdiction
    0.81
    Act Density 0.064%

    No Known Activations