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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deep exploration, investigation, or analysis

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to exploration and analysis of depth or complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    move
    -0.71
    kees
    -0.67
    oppable
    -0.66
    iannopoulos
    -0.66
    apest
    -0.64
    click
    -0.63
    Frames
    -0.61
    winner
    -0.59
    rily
    -0.59
    voice
    -0.59
    POSITIVE LOGITS
     trenches
    1.20
     depths
    1.19
     deeper
    1.10
     pockets
    1.09
     recess
    1.03
     deepest
    0.97
     depth
    0.95
     deep
    0.92
     darkest
    0.91
     roots
    0.91
    Act Density 0.273%

    No Known Activations