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

    Neuronpedia

    INDEX
    Explanations

    information related to chemical compounds or physical structures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various chemical compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipeg
    -0.82
    hips
    -0.77
    waukee
    -0.71
     Sparrow
    -0.70
    Ŀ
    -0.67
    ockets
    -0.67
     Gunn
    -0.67
    hhhh
    -0.66
    ï¸
    -0.66
     Hector
    -0.66
    POSITIVE LOGITS
    inct
    0.81
     compounds
    0.80
     annex
    0.76
    alities
    0.74
     compound
    0.73
    aque
    0.69
    ogen
    0.69
    iliary
    0.66
     fractures
    0.66
     oxide
    0.66
    Act Density 0.019%

    No Known Activations