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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to direct personal experience or involvement

    oai_token-act-pair · gpt-3.5-turbo

    words related to firsthand experiences or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nam
    -0.76
    oslav
    -0.70
    oleon
    -0.67
    ervative
    -0.66
    pty
    -0.66
    pload
    -0.66
    anson
    -0.65
    lua
    -0.64
    liam
    -0.63
    asty
    -0.63
    POSITIVE LOGITS
     knowledge
    0.73
    Witness
    0.71
    sight
    0.71
    £ı
    0.67
     recordings
    0.67
     FAC
    0.66
    senal
    0.66
     realities
    0.65
     realization
    0.65
    ©¶æ
    0.65
    Act Density 0.044%

    No Known Activations