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

    Neuronpedia

    INDEX
    Explanations

    programming code syntax related to function definitions and instructions

    oai_token-act-pair · gpt-3.5-turbo

    closing parentheses and colons in code-like structures or syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enta
    -0.84
    ishly
    -0.77
    ijk
    -0.77
    ellery
    -0.74
    shaw
    -0.74
    sett
    -0.72
    bett
    -0.70
    itably
    -0.70
    ifying
    -0.69
    uve
    -0.69
    POSITIVE LOGITS
    ::::::::
    0.85
    *:
    0.83
    :{
    0.77
    ,,,,,,,,
    0.64
    ":-
    0.64
     ""
    0.61
    ""
    0.61
     ???
    0.60
     Duration
    0.59
     Replacement
    0.58
    Act Density 0.026%

    No Known Activations