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

    Neuronpedia

    INDEX
    Explanations

    references to personal and social relationships impacted by various challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adem
    -0.16
    anou
    -0.15
     KiÅŁisel
    -0.15
    akin
    -0.15
    loub
    -0.14
    assen
    -0.14
    ripper
    -0.14
    dez
    -0.14
    keh
    -0.14
    wers
    -0.13
    POSITIVE LOGITS
     directly
    0.26
     differently
    0.25
     indirectly
    0.20
    缴æİ¥
    0.18
     напÑĢÑıм
    0.18
     negatively
    0.18
     adversely
    0.18
    idor
    0.17
     indirect
    0.17
     ways
    0.15
    Act Density 0.112%

    No Known Activations