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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "tend" and its variations that reflect emotional connections or predispositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aving
    -0.18
    aven
    -0.16
    vide
    -0.16
    248
    -0.16
    ivas
    -0.15
    ime
    -0.14
    Å¡t
    -0.14
    vation
    -0.14
    éric
    -0.14
    orative
    -0.14
    POSITIVE LOGITS
    erness
    0.30
    entious
    0.23
    ENCIES
    0.23
    ril
    0.19
    ENCY
    0.18
    encias
    0.17
    prene
    0.16
    SURE
    0.16
    entially
    0.16
     tend
    0.16
    Act Density 0.006%

    No Known Activations