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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating assumptions or presumptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating assumptions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HCR
    -0.82
    nels
    -0.75
    FTWARE
    -0.73
    sung
    -0.72
    aina
    -0.72
    psey
    -0.71
    sterdam
    -0.70
    vertisement
    -0.69
    talking
    -0.67
    velength
    -0.66
    POSITIVE LOGITS
     responsibility
    0.83
     innocence
    0.80
     ownership
    0.79
     liability
    0.75
     assume
    0.75
     incorrectly
    0.71
     that
    0.71
     familiarity
    0.71
     infall
    0.70
     paternity
    0.69
    Act Density 0.042%

    No Known Activations