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

    Neuronpedia

    INDEX
    Explanations

    keywords or phrases related to a wide variety or range of items

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases emphasizing diversity and breadth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LV
    -0.73
    CB
    -0.72
    aminer
    -0.67
    ilater
    -0.65
    Lv
    -0.64
    ICAN
    -0.63
    cair
    -0.62
    åĤ
    -0.62
    act
    -0.61
    IENCE
    -0.61
    POSITIVE LOGITS
    leaf
    1.03
     wide
    0.98
    sheets
    0.92
     wider
    0.82
     scope
    0.80
     variety
    0.80
     widened
    0.77
     eyed
    0.77
     breadth
    0.76
    creen
    0.76
    Act Density 0.010%

    No Known Activations