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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate ongoing or repeated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hold
    -0.67
     work
    -0.61
     cover
    -0.60
     call
    -0.58
     hunting
    -0.57
     binding
    -0.57
     output
    -0.57
     training
    -0.56
     supply
    -0.55
     coaching
    -0.55
    POSITIVE LOGITS
     realising
    1.45
     agreeing
    1.37
     preferring
    1.37
     realizing
    1.35
     admitting
    1.34
     arriving
    1.34
     recognising
    1.31
     leaving
    1.30
     omitting
    1.28
     appearing
    1.23
    Act Density 0.420%

    No Known Activations