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

    Neuronpedia

    INDEX
    Explanations

    terms related to inner and outer spaces or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andan
    -0.17
    sin
    -0.17
    iec
    -0.17
    ron
    -0.16
    sdale
    -0.15
    yny
    -0.15
    services
    -0.14
    spar
    -0.14
    spot
    -0.14
    enz
    -0.14
    POSITIVE LOGITS
    most
    0.45
    halb
    0.30
    -most
    0.25
    MOST
    0.25
     most
    0.22
    -inner
    0.22
    wear
    0.20
    /ext
    0.20
    ds
    0.20
    .Inner
    0.19
    Act Density 0.017%

    No Known Activations