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

    Neuronpedia

    INDEX
    Explanations

    terms indicating approximation or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seasons
    -0.16
    æļ
    -0.15
    eter
    -0.14
    ÑĢÑĥÑĩ
    -0.14
    wards
    -0.14
    ilon
    -0.14
     Ensemble
    -0.14
    eward
    -0.14
    947
    -0.14
    214
    -0.14
    POSITIVE LOGITS
     everyone
    0.27
     everybody
    0.26
     exclusively
    0.25
     always
    0.25
    everyone
    0.23
     everything
    0.23
     every
    0.22
     certainly
    0.22
     anyone
    0.22
     all
    0.22
    Act Density 0.040%

    No Known Activations