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

    Neuronpedia

    INDEX
    Explanations

    sections related to software licensing and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dot
    -1.52
    ever
    -1.34
    ogle
    -1.33
     blocking
    -1.32
     hack
    -1.25
     ctrl
    -1.24
     bear
    -1.24
    bracket
    -1.22
    emitter
    -1.20
     depression
    -1.20
    POSITIVE LOGITS
    ittal
    1.69
    wagen
    1.67
    usal
    1.53
    £
    1.49
    ].)
    1.49
    ³
    1.44
    imes
    1.43
    mith
    1.41
    ues
    1.40
    ischen
    1.39
    Act Density 0.100%

    No Known Activations