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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "follow" and its variations in different contexts

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

    following rules or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.58
     Maschine
    -0.54
    Machines
    -0.53
     dermatologist
    -0.53
    évaluateur
    -0.53
    machines
    -0.52
     Machines
    -0.52
     [*]
    -0.52
    melons
    -0.52
    nically
    -0.51
    POSITIVE LOGITS
     follow
    1.90
     Follow
    1.84
    follow
    1.81
    Follow
    1.77
     FOLLOW
    1.60
     follows
    1.51
    follows
    1.41
     Follows
    1.41
    FOLLOW
    1.40
     followed
    1.26
    Act Density 0.035%

    No Known Activations