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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating potential actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Winds
    -0.17
    hn
    -0.16
    istas
    -0.16
    kers
    -0.15
     themselves
    -0.15
    ilib
    -0.15
    w
    -0.15
    hor
    -0.15
    ilde
    -0.14
    .snap
    -0.14
    POSITIVE LOGITS
    iner
    0.26
     raining
    0.25
    chy
    0.20
    alo
    0.19
    eless
    0.19
    edn
    0.18
    alic
    0.17
    ty
    0.17
    chalk
    0.17
    Lane
    0.17
    Act Density 0.158%

    No Known Activations