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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    oai_token-act-pair · gpt-3.5-turbo

    specific days of the week and dates in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clusions
    -0.62
    omic
    -0.59
    push
    -0.58
    addons
    -0.57
    notations
    -0.57
     ])
    -0.56
    ãĥ¤
    -0.55
    HAHAHAHA
    -0.54
    UTF
    -0.54
    pires
    -0.54
    POSITIVE LOGITS
     aboard
    0.86
     at
    0.78
     near
    0.75
     inside
    0.74
     atop
    0.73
     outside
    0.73
     against
    0.72
     in
    0.72
     flanked
    0.71
     across
    0.69
    Act Density 0.258%

    No Known Activations