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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation and support in written communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    field
    -0.20
     field
    -0.18
     Field
    -0.16
    ush
    -0.15
    ca
    -0.15
     Gron
    -0.15
     Ca
    -0.15
     crib
    -0.15
    FIELD
    -0.14
    -0.14
    POSITIVE LOGITS
    rava
    0.17
    esson
    0.16
    [assembly
    0.15
    ëŁ
    0.15
    Nonnull
    0.15
    htub
    0.15
    åīĽ
    0.15
    emann
    0.15
    arseille
    0.15
    ARGIN
    0.14
    Act Density 0.078%

    No Known Activations