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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media and news platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recomp
    -0.67
     bragging
    -0.66
    VIDIA
    -0.65
     evapor
    -0.63
     notor
    -0.63
     unrecogn
    -0.63
     mism
    -0.62
     aborted
    -0.61
    forced
    -0.60
     scapego
    -0.60
    POSITIVE LOGITS
    Follow
    0.82
    Dispatch
    0.76
     on
    0.73
    Tips
    0.72
     securely
    0.71
    Ô
    0.70
     (@
    0.68
     actionGroup
    0.68
     Follow
    0.67
    tan
    0.67
    Act Density 0.082%

    No Known Activations