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

    Neuronpedia

    INDEX
    Explanations

    actions involving holding and physical interactions with objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.43
    $_['
    -0.41
    ThroughAttribute
    -0.40
    ubscribe
    -0.38
     ddelweddau
    -0.37
    ValueStyle
    -0.36
    principalTable
    -0.36
    /*---
    -0.34
     fieldNum
    -0.34
     prover
    -0.34
    POSITIVE LOGITS
     handheld
    0.64
     Händen
    0.62
     ModelExpression
    0.60
    weapon
    0.59
     Hände
    0.58
     hands
    0.57
     weapon
    0.57
     wielded
    0.56
     wielding
    0.55
    手里
    0.54
    Act Density 0.510%

    No Known Activations