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

    Neuronpedia

    INDEX
    Explanations

    phrases related to introductory information about various topics

    oai_token-act-pair · gpt-3.5-turbo

    references to 'About' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oly
    -0.82
    rift
    -0.76
    rang
    -0.70
    åĤ
    -0.69
    apt
    -0.68
    à¥
    -0.67
    hiba
    -0.66
    egal
    -0.66
    ergic
    -0.66
    ¯¯¯¯¯¯¯¯
    -0.65
    POSITIVE LOGITS
     Us
    0.89
     Citation
    0.76
     Paste
    0.72
    About
    0.70
     About
    0.69
    ahime
    0.69
    aleb
    0.68
     Climate
    0.67
     Stories
    0.66
     WATCHED
    0.66
    Act Density 0.046%

    No Known Activations