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

    Neuronpedia

    INDEX
    Explanations

    references to an audience or engagement with an audience

    oai_token-act-pair · gpt-3.5-turbo

    references to audio content or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cloth
    -0.68
     antidepressants
    -0.66
     Warriors
    -0.64
    OPLE
    -0.63
    tons
    -0.63
     Spice
    -0.61
     everything
    -0.59
     Tend
    -0.59
     eternal
    -0.59
     LINE
    -0.57
    POSITIVE LOGITS
    ience
    1.24
    iences
    1.18
    iov
    1.12
    Aud
    1.02
    ienced
    0.98
    obook
    0.94
    enfranch
    0.94
    itory
    0.93
    yssey
    0.92
    Reviewer
    0.90
    Act Density 0.009%

    No Known Activations