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

    Neuronpedia

    INDEX
    Explanations

    phrases or mentions related to offering things for free

    oai_token-act-pair · gpt-3.5-turbo

    references to free offerings or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    need
    -0.76
    itect
    -0.75
     Takeru
    -0.71
    ulous
    -0.70
    ENTION
    -0.70
    onductor
    -0.68
    arre
    -0.68
     Matters
    -0.66
    emet
    -0.65
    assis
    -0.65
    POSITIVE LOGITS
    bies
    1.23
    bie
    1.01
     downloadable
    0.89
     roam
    0.88
    zes
    0.86
    zers
    0.83
    zing
    0.83
     download
    0.80
     unlimited
    0.76
     unconditional
    0.76
    Act Density 0.031%

    No Known Activations