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

    Neuronpedia

    INDEX
    Explanations

    nouns and their descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.17
     seins
    -0.16
     entries
    -0.16
     findings
    -0.15
    alog
    -0.15
    crm
    -0.14
    OnError
    -0.14
    eldon
    -0.14
    otech
    -0.13
    anga
    -0.13
    POSITIVE LOGITS
     woman
    0.20
     lump
    0.17
     young
    0.17
     sign
    0.16
     pair
    0.16
    young
    0.16
     lone
    0.16
     contingent
    0.16
     group
    0.16
     cloud
    0.16
    Act Density 0.305%

    No Known Activations