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

    Neuronpedia

    INDEX
    Explanations

    proper names preceded by special characters designated by 'Ċ' followed by numerical values

    oai_token-act-pair · gpt-3.5-turbo

    highly notable or dramatic events, particularly those involving crime or legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.72
    heit
    -0.67
    utical
    -0.63
     manoeuv
    -0.63
     secondly
    -0.61
    pan
    -0.60
    gren
    -0.60
    course
    -0.59
     agility
    -0.59
     dissu
    -0.59
    POSITIVE LOGITS
    arta
    0.96
    neau
    0.71
    Specifically
    0.71
    SEE
    0.68
     Billboard
    0.67
    SHARE
    0.67
     Deadline
    0.66
    Rh
    0.64
    Beginning
    0.64
    WASHINGTON
    0.63
    Act Density 0.275%

    No Known Activations