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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases indicating action or belief

    oai_token-act-pair · gpt-3.5-turbo

    expressions of belief and awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.72
    iven
    -0.72
    oney
    -0.61
     Authors
    -0.56
    yssey
    -0.56
    UNCH
    -0.56
    zik
    -0.56
    vertisement
    -0.55
    ERAL
    -0.55
    HAM
    -0.55
    POSITIVE LOGITS
    pires
    0.82
     MFT
    0.65
    leground
    0.64
    verages
    0.63
     milit
    0.63
    lege
    0.61
     defect
    0.61
     contrace
    0.61
     misfortune
    0.61
     legitimately
    0.60
    Act Density 0.330%

    No Known Activations