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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "follow" and its variations indicating tracking or adherence to something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yag
    -0.76
     McCarty
    -0.75
     Urqu
    -0.74
    oldValue
    -0.73
     Eisenberg
    -0.72
     Jacobsen
    -0.70
    mbolos
    -0.70
     Veld
    -0.68
     Pemberton
    -0.67
     Ephraim
    -0.66
    POSITIVE LOGITS
     Follows
    1.69
     follows
    1.57
    follow
    1.56
     follow
    1.51
     FOLLOW
    1.50
    Follow
    1.48
    follows
    1.45
     Follow
    1.43
     Followed
    1.35
    Followed
    1.33
    Act Density 0.145%

    No Known Activations