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

    Neuronpedia

    INDEX
    Explanations

    hints or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "hint" indicating suggestions or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    frey
    -0.74
    ccording
    -0.73
    nea
    -0.71
    ocker
    -0.70
    artney
    -0.69
    bred
    -0.68
    vict
    -0.67
    Cross
    -0.65
    vez
    -0.64
     Kinnikuman
    -0.63
    POSITIVE LOGITS
     hint
    1.49
     hints
    1.36
     clue
    0.88
     clues
    0.85
     glimps
    0.82
     hinted
    0.82
     wink
    0.80
    llor
    0.77
     warning
    0.73
    itives
    0.73
    Act Density 0.016%

    No Known Activations