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

    Neuronpedia

    INDEX
    Explanations

    references to future plans or intentions

    oai_token-act-pair · gpt-3.5-turbo

    references to future intentions or arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inas
    -0.71
     ILCS
    -0.64
    mint
    -0.63
    odox
    -0.63
    Cause
    -0.62
    inion
    -0.60
    entimes
    -0.60
     Syndrome
    -0.60
    avery
    -0.59
     Governors
    -0.59
    POSITIVE LOGITS
     for
    0.90
    isphere
    0.88
     hatched
    0.81
    emaker
    0.81
     underway
    0.78
     unveiled
    0.76
     horizon
    0.73
     ahead
    0.73
     to
    0.73
    etting
    0.72
    Act Density 0.064%

    No Known Activations