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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific subject "Romanesque" architecture

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific class of animals or traits associated with animal behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itude
    -0.93
    mie
    -0.89
    ENC
    -0.83
    ECH
    -0.78
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.77
    kson
    -0.76
    iday
    -0.72
    anwhile
    -0.72
     Thatcher
    -0.71
    dies
    -0.70
    POSITIVE LOGITS
    layer
    0.82
    zac
    0.77
    elaide
    0.76
    aukee
    0.75
    ragon
    0.74
    lator
    0.72
    sexual
    0.71
    chwitz
    0.70
    wright
    0.70
    izoph
    0.69
    Act Density 0.021%

    No Known Activations