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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating social or relational dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AGO
    -0.17
     automáticamente
    -0.16
     lou
    -0.15
    ÑĢож
    -0.15
    ILER
    -0.14
    odore
    -0.14
     {}.
    -0.14
    .mods
    -0.14
    /Foundation
    -0.14
     automatic
    -0.13
    POSITIVE LOGITS
    stype
    0.16
    ham
    0.15
     tradition
    0.15
     flush
    0.14
    utsch
    0.14
    bd
    0.14
    hof
    0.14
    BD
    0.13
     Cop
    0.13
    iang
    0.13
    Act Density 0.065%

    No Known Activations