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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "follow" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "follow" and related words

    np_acts-logits-general · gemini-2.0-flash

    following instructions, advice, or people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    примеча
    -0.59
     Greenfield
    -0.56
    Sparks
    -0.55
     Dink
    -0.55
    ielles
    -0.55
    ★☆
    -0.54
     Yag
    -0.54
     McCarty
    -0.54
     Sparks
    -0.53
    oldValue
    -0.53
    POSITIVE LOGITS
     Follows
    1.24
     FOLLOW
    1.19
    follow
    1.14
     follow
    1.14
     follows
    1.13
    Followed
    1.13
    Follow
    1.11
     Follow
    1.08
     Followed
    1.07
    follows
    1.05
    Act Density 0.124%

    No Known Activations