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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical and structured topics, possibly in a list format

    oai_token-act-pair · gpt-3.5-turbo

    structures related to various topics and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -1.12
    uly
    -0.72
    boro
    -0.65
    abouts
    -0.64
    ennes
    -0.64
    dn
    -0.62
    lected
    -0.62
    etta
    -0.62
    acan
    -0.62
    ilipp
    -0.62
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.95
    ³³³³³³³³
    0.82
    ³³³
    0.75
    ccording
    0.69
    ³³³³
    0.63
    ³³
    0.63
    ãĤ¨ãĥ«
    0.61
     Edit
    0.60
     marrow
    0.59
     Appearance
    0.59
    Act Density 0.215%

    No Known Activations