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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong opinions or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    URI
    -0.15
     ÑĤол
    -0.14
    _argv
    -0.14
     Stable
    -0.14
    pong
    -0.14
    lsen
    -0.14
     conscient
    -0.13
     Convers
    -0.13
     Disposable
    -0.13
     mutable
    -0.13
    POSITIVE LOGITS
     strong
    0.28
     sharp
    0.25
     ac
    0.25
     vir
    0.24
     forth
    0.23
     force
    0.23
     ca
    0.23
     measured
    0.23
     pointed
    0.23
     vit
    0.23
    Act Density 0.239%

    No Known Activations