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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "follow" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ielles
    -0.64
     Sparks
    -0.62
     McCarty
    -0.60
    ynka
    -0.60
     bahawa
    -0.59
     Dink
    -0.58
     melting
    -0.58
     kepad
    -0.57
     Melting
    -0.57
     Greenfield
    -0.57
    POSITIVE LOGITS
     Follows
    1.30
     follows
    1.16
     FOLLOW
    1.16
    Followed
    1.16
    Follow
    1.16
    follow
    1.16
     follow
    1.14
    follows
    1.10
     Follow
    1.10
     Followed
    1.07
    Act Density 0.141%

    No Known Activations