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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an urge or motivation to encourage action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RuleContext
    -0.67
    rüstung
    -0.61
    рома
    -0.59
     spect
    -0.58
    Spectrum
    -0.56
     portátil
    -0.55
    qrstuvwxyz
    -0.55
    getOptions
    -0.55
    cerna
    -0.55
     Diana
    -0.55
    POSITIVE LOGITS
     push
    3.67
     Push
    3.24
     pushes
    3.11
     pushed
    3.10
     pushing
    3.07
     PUSH
    3.07
    Push
    2.94
     Pushing
    2.93
    push
    2.90
    Pushing
    2.79
    Act Density 0.055%

    No Known Activations