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

    Neuronpedia

    INDEX
    Explanations

    the phrase "not to mention"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "not to mention."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    accompan
    -0.76
    lines
    -0.67
    machine
    -0.67
    checks
    -0.65
    holding
    -0.63
     millenn
    -0.63
    going
    -0.63
    eros
    -0.61
    furt
    -0.60
    ero
    -0.60
    POSITIVE LOGITS
     mention
    1.56
     worry
    0.93
     offend
    0.92
     exceed
    0.90
     bother
    0.86
    asted
    0.83
    asters
    0.81
     diminish
    0.75
     interfere
    0.73
     condone
    0.73
    Act Density 0.075%

    No Known Activations