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

    Neuronpedia

    INDEX
    Explanations

    words related to "sign" or "signify."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ync
    -0.16
    ule
    -0.15
    imps
    -0.15
    iggins
    -0.14
    enate
    -0.14
    inta
    -0.14
    brain
    -0.14
     Bal
    -0.14
    ted
    -0.14
    rena
    -0.14
    POSITIVE LOGITS
    ificance
    0.31
    ificantly
    0.30
    atures
    0.27
    ificant
    0.27
    atories
    0.22
    alled
    0.20
    aling
    0.20
    iture
    0.19
    reed
    0.19
    post
    0.19
    Act Density 0.040%

    No Known Activations