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

    Neuronpedia

    INDEX
    Explanations

    words relating to confinement or restriction

    oai_token-act-pair · gpt-3.5-turbo

    words that describe various attributes or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dfx
    -0.76
    âĸ¬âĸ¬
    -0.72
    doctor
    -0.68
    ERA
    -0.68
    ËĪ
    -0.67
    ellen
    -0.67
    OWS
    -0.65
     sharper
    -0.64
    PsyNetMessage
    -0.63
    ADE
    -0.62
    POSITIVE LOGITS
    ous
    1.28
    Magikarp
    1.10
    ity
    0.87
    idal
    0.81
    ities
    0.80
    ivil
    0.80
    atile
    0.79
    lihood
    0.78
    entials
    0.77
    ious
    0.76
    Act Density 0.011%

    No Known Activations