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

    Neuronpedia

    INDEX
    Explanations

    actions related to throwing or discarding objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    behörde
    -0.61
     grotte
    -0.60
    ecap
    -0.59
     Kell
    -0.59
     Sant
    -0.59
     signore
    -0.57
     huellas
    -0.57
     Besch
    -0.53
    従
    -0.53
    madol
    -0.53
    POSITIVE LOGITS
     throw
    1.63
     thrown
    1.48
     Throw
    1.45
     throwing
    1.40
    Throw
    1.37
     threw
    1.36
     throws
    1.36
    thrown
    1.27
    throwing
    1.24
     toss
    1.23
    Act Density 0.151%

    No Known Activations