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

    Neuronpedia

    INDEX
    Explanations

    conditional statements starting with "Unless"

    oai_token-act-pair · gpt-3.5-turbo

    the word "unless" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARC
    -0.80
    ery
    -0.73
    ulate
    -0.71
    sequence
    -0.69
    enos
    -0.68
    pour
    -0.67
    idespread
    -0.66
     Decay
    -0.65
    Maker
    -0.64
    ults
    -0.64
    POSITIVE LOGITS
    soever
    1.00
     otherwise
    0.98
    wcsstore
    0.85
    fy
    0.80
     indemn
    0.80
     expressly
    0.69
     strictly
    0.69
    agons
    0.66
     specially
    0.65
     stip
    0.64
    Act Density 0.014%

    No Known Activations