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

    Neuronpedia

    INDEX
    Explanations

    complex words related to compounds, some of which are chemical in nature

    oai_token-act-pair · gpt-3.5-turbo

    references to chemical compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hips
    -0.79
    hhhh
    -0.76
    ipeg
    -0.76
    HH
    -0.69
    DW
    -0.68
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.67
    waukee
    -0.67
     Jere
    -0.65
    ı
    -0.65
    ockets
    -0.64
    POSITIVE LOGITS
    inct
    0.81
     compounds
    0.74
     annex
    0.72
     compound
    0.70
    ilation
    0.70
    opath
    0.68
    aque
    0.67
    alities
    0.67
    notes
    0.66
    iliar
    0.65
    Act Density 0.017%

    No Known Activations