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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical conflict or confrontation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.70
     autorytatywna
    -0.68
     []:
    -0.59
    IntoConstraints
    -0.56
    usehen
    -0.55
     Italijanski
    -0.54
    EndGlobalSection
    -0.53
     snippetHide
    -0.53
    <?
    -0.52
    usstsein
    -0.52
    POSITIVE LOGITS
     punches
    0.96
     fists
    0.96
     punching
    0.90
     punch
    0.88
     punched
    0.84
    punch
    0.83
     fist
    0.83
     brawl
    0.80
     melee
    0.78
     agresión
    0.77
    Act Density 0.248%

    No Known Activations