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

    Neuronpedia

    INDEX
    Explanations

    references to horns or horned animals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gn
    -0.19
    hta
    -0.16
    gart
    -0.16
    genic
    -0.15
    gni
    -0.15
    teri
    -0.14
    tere
    -0.14
    zure
    -0.14
    caret
    -0.14
     spot
    -0.14
    POSITIVE LOGITS
    beam
    0.25
    pipe
    0.25
    aday
    0.23
    ung
    0.23
    ed
    0.23
    ady
    0.21
    bill
    0.21
    et
    0.21
    itos
    0.21
    bl
    0.20
    Act Density 0.021%

    No Known Activations