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

    Neuronpedia

    INDEX
    Explanations

    terms related to authentication and access tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovol
    -0.16
    apons
    -0.15
     policym
    -0.15
    erek
    -0.14
    estro
    -0.14
    ahrenheit
    -0.14
    .Small
    -0.14
    dent
    -0.14
    room
    -0.13
     dap
    -0.13
    POSITIVE LOGITS
    chal
    0.16
    ized
    0.16
    chia
    0.16
     Haram
    0.15
    icina
    0.14
    declspec
    0.14
    zÅij
    0.14
    ised
    0.14
     airs
    0.14
    exus
    0.14
    Act Density 0.010%

    No Known Activations