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

    Neuronpedia

    INDEX
    Explanations

    internet links or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to technical specifications and product details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hatt
    -0.89
    ipp
    -0.83
     Hicks
    -0.82
     hous
    -0.72
    34
    -0.72
    HEAD
    -0.69
     Aid
    -0.69
     ank
    -0.68
     Inher
    -0.67
    414
    -0.67
    POSITIVE LOGITS
    V
    1.46
    v
    1.38
    VE
    1.30
    ve
    1.29
    VP
    1.25
    Vs
    1.24
    vez
    1.23
    va
    1.22
    vent
    1.20
    vest
    1.18
    Act Density 0.416%

    No Known Activations