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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing 'right', often in the context of individual autonomy or correctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amba
    -0.69
    jug
    -0.68
    gur
    -0.64
    cussion
    -0.64
    âĢ²
    -0.62
    cery
    -0.61
    uve
    -0.61
    lymp
    -0.61
    ÅĤ
    -0.61
    sung
    -0.61
    POSITIVE LOGITS
     selves
    0.80
     counterparts
    0.69
     temperament
    0.67
    imei
    0.63
     quirks
    0.63
     predic
    0.63
     therap
    0.63
     styles
    0.63
     creations
    0.63
    blance
    0.62
    Act Density 0.154%

    No Known Activations