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

    Neuronpedia

    INDEX
    Explanations

    references to various types of tools

    oai_token-act-pair · gpt-3.5-turbo

    references to various tools and their uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sons
    -0.78
    ometown
    -0.69
     millenn
    -0.64
    erest
    -0.64
     Parables
    -0.63
    ervation
    -0.62
    orus
    -0.61
    omes
    -0.60
    IGH
    -0.60
    idential
    -0.60
    POSITIVE LOGITS
    tips
    1.44
    kit
    1.21
    tip
    1.07
     tool
    0.97
     guiActiveUn
    0.94
    matically
    0.94
     tools
    0.92
    belt
    0.89
    sonian
    0.86
    Tip
    0.83
    Act Density 0.012%

    No Known Activations