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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "pull"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RouterModule
    -0.61
    PrototypeOf
    -0.59
     مشين
    -0.58
    uminense
    -0.55
     Apos
    -0.54
    rophoresis
    -0.53
     szóci
    -0.52
    hyrchwyd
    -0.52
     elektronik
    -0.52
    MethodManager
    -0.51
    POSITIVE LOGITS
     pull
    1.62
    pull
    1.55
     pulls
    1.49
     Pull
    1.47
    Pull
    1.47
     PULL
    1.42
     pulling
    1.37
     pulled
    1.35
    PULL
    1.26
    pulled
    1.21
    Act Density 0.063%

    No Known Activations