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

    Neuronpedia

    INDEX
    Explanations

    medical terms and procedures, such as "coroner," "vomiting," "fever," "brain damage," and "open wounds."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal and institutional outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.63
     nutshell
    -0.61
    Gender
    -0.55
    Growing
    -0.52
    çļ
    -0.52
     Parables
    -0.51
    anka
    -0.51
    eno
    -0.51
    osher
    -0.50
    ertain
    -0.50
    POSITIVE LOGITS
     resumed
    0.74
     regained
    0.73
     restart
    0.70
     reapp
    0.68
     withdrawals
    0.68
     subsequent
    0.66
     exhaustion
    0.66
     reverted
    0.65
     reinstated
    0.65
     rede
    0.63
    Act Density 1.508%

    No Known Activations