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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating a lack of concern or disregard

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong sentiment or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edIn
    -0.78
    yrinth
    -0.71
    taboola
    -0.66
    _-
    -0.66
    Wik
    -0.64
    iba
    -0.63
    Ct
    -0.63
    anian
    -0.63
    nel
    -0.61
     Gaal
    -0.60
    POSITIVE LOGITS
     impression
    0.86
    icum
    0.80
     amnesty
    0.73
    chance
    0.73
     advice
    0.72
     counsel
    0.69
     commencement
    0.66
     signal
    0.65
     keynote
    0.65
     pause
    0.64
    Act Density 0.222%

    No Known Activations