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

    Neuronpedia

    INDEX
    Explanations

    uppercase words or initials

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or shorthand terms typically used in formal or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whats
    -0.67
    issues
    -0.64
    doctor
    -0.63
    Reviewer
    -0.63
    protection
    -0.59
    eps
    -0.59
     davidjl
    -0.58
    primary
    -0.57
    anus
    -0.57
     operators
    -0.56
    POSITIVE LOGITS
    ividual
    0.97
    pport
    0.81
    inately
    0.80
    urities
    0.76
    umerable
    0.71
    ocent
    0.70
    iever
    0.69
     midst
    0.68
    entials
    0.68
    itably
    0.67
    Act Density 0.090%

    No Known Activations