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

    Neuronpedia

    INDEX
    Explanations

    verbs related to influencing or affecting something

    oai_token-act-pair · gpt-3.5-turbo

    actions or concepts related to vision and observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Legions
    -0.68
    rophe
    -0.67
     Named
    -0.66
    KT
    -0.65
    alion
    -0.64
    Offic
    -0.64
     Nem
    -0.63
    Games
    -0.63
    isd
    -0.63
     Byrd
    -0.62
    POSITIVE LOGITS
     dressing
    0.84
    waters
    0.83
     cooling
    0.79
    upt
    0.75
     immersion
    0.75
    coat
    0.74
    mental
    0.74
     coat
    0.71
     flow
    0.71
     fluid
    0.71
    Act Density 0.137%

    No Known Activations