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

    Neuronpedia

    INDEX
    Explanations

    references to insanity and mental health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cyfeiriadau
    -0.64
     snippetHide
    -0.56
    andExpect
    -0.52
     Sting
    -0.52
     cerevisiae
    -0.51
     Hesper
    -0.51
     pulumi
    -0.51
     %>
    -0.49
    TopLeft
    -0.49
     pectoral
    -0.47
    POSITIVE LOGITS
     mental
    1.33
     psychiatric
    1.22
     Mental
    1.19
     Psychiatric
    1.14
    Mental
    1.13
     Psychiatry
    1.11
     insanity
    1.11
     psychiatry
    1.09
     psychiat
    1.08
     madness
    1.07
    Act Density 0.325%

    No Known Activations