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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and specific places or entities

    oai_token-act-pair · gpt-3.5-turbo

    entities related to prominent public figures and organizations, particularly in relation to politics and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     omit
    -0.55
    fters
    -0.54
    ©¶æ
    -0.54
    Topics
    -0.53
     disparate
    -0.50
    fter
    -0.50
    rocal
    -0.50
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.49
    alyses
    -0.49
     contemporaries
    -0.49
    POSITIVE LOGITS
    *.
    0.89
    .[
    0.85
    .</
    0.84
    .
    0.84
    _.
    0.82
    .ãĢį
    0.79
     itself
    0.78
    .–
    0.78
    !.
    0.76
    !!!!!!!!
    0.75
    Act Density 1.011%

    No Known Activations