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

    Neuronpedia

    INDEX
    Explanations

    capital letters with non-alphabet characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or actions that indicate critical moments or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.71
    abouts
    -0.66
     endeavour
    -0.64
     Thornton
    -0.63
     Ferdinand
    -0.61
    hene
    -0.61
     brunt
    -0.60
    anium
    -0.60
     enrol
    -0.59
     emancipation
    -0.59
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.98
    SCP
    0.83
    ³³³³³³³³
    0.83
    Ingredients
    0.83
    https
    0.82
    Liter
    0.81
    Looks
    0.80
    WARNING
    0.80
    ³³³³
    0.78
    Feature
    0.78
    Act Density 0.135%

    No Known Activations