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

    Neuronpedia

    INDEX
    Explanations

    descriptions of violent or distressing situations

    oai_token-act-pair · gpt-3.5-turbo

    sentences that reflect negative or controversial subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omics
    -0.80
     compact
    -0.76
     glow
    -0.74
     purse
    -0.73
     marketplace
    -0.72
     hatch
    -0.71
     zone
    -0.71
     defe
    -0.71
     ecosystem
    -0.70
     quir
    -0.69
    POSITIVE LOGITS
     Needless
    1.30
     Similarly
    1.23
     Afterwards
    1.22
     Likewise
    1.21
     Additionally
    1.21
     However
    1.20
     Ironically
    1.19
     Meanwhile
    1.18
     Later
    1.17
     Apparently
    1.16
    Act Density 0.993%

    No Known Activations