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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "wolf" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agger
    -0.23
    iros
    -0.17
    abler
    -0.16
    寧
    -0.15
    abant
    -0.15
    velte
    -0.14
    incinn
    -0.14
    ora
    -0.14
    arrow
    -0.14
    /left
    -0.14
    POSITIVE LOGITS
    owitz
    0.23
    enso
    0.22
    pack
    0.22
    enstein
    0.22
    enden
    0.21
    hound
    0.21
    endale
    0.20
    ishly
    0.19
    SSL
    0.18
    sonian
    0.18
    Act Density 0.008%

    No Known Activations