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

    Neuronpedia

    INDEX
    Explanations

    words related to refurbishing or renovating something

    oai_token-act-pair · gpt-3.5-turbo

    words associated with reference and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Merit
    -0.74
     Sabha
    -0.69
     Slater
    -0.66
    TAG
    -0.64
    代
    -0.63
    Prince
    -0.61
    nets
    -0.61
    Priv
    -0.60
    ubuntu
    -0.60
     disadvant
    -0.59
    POSITIVE LOGITS
    itory
    0.81
    glers
    0.77
    ndum
    0.74
    hetti
    0.73
    ascript
    0.70
    vernment
    0.70
    ction
    0.67
    icably
    0.66
     hairs
    0.66
    nyder
    0.65
    Act Density 0.048%

    No Known Activations