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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds or molecular structures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific chemical compounds, particularly those containing "OH"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    guard
    -0.80
    ãĥ¼ãĥĨãĤ£
    -0.80
    eering
    -0.74
    unct
    -0.71
    ãĥķ
    -0.70
    cape
    -0.68
    kaya
    -0.66
    ãĥ¯
    -0.65
    ularity
    -0.65
     totality
    -0.64
    POSITIVE LOGITS
    OH
    1.18
    FU
    1.01
    OF
    0.96
    OME
    0.94
    ONT
    0.91
    OM
    0.87
    OE
    0.87
    ISTORY
    0.87
    OOD
    0.86
    CI
    0.85
    Act Density 0.009%

    No Known Activations