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

    Neuronpedia

    INDEX
    Explanations

    words related to chemical compounds and substances

    oai_token-act-pair · gpt-3.5-turbo

    specific types of biological or chemical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \\\\\\\\
    -0.75
    ificantly
    -0.70
    wise
    -0.70
    Attempts
    -0.68
    =]
    -0.67
    Specific
    -0.67
    verified
    -0.67
    Lear
    -0.66
    FLAG
    -0.65
    -+-+
    -0.63
    POSITIVE LOGITS
    cape
    1.08
    cale
    1.04
    etter
    1.04
     themselves
    0.99
    heet
    0.96
    hip
    0.96
    mith
    0.95
    hirt
    0.94
    etting
    0.94
    pring
    0.92
    Act Density 0.534%

    No Known Activations