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

    Neuronpedia

    INDEX
    Explanations

    words related to discussing topics or subjects

    oai_token-act-pair · gpt-3.5-turbo

    topics related to discussions in media or broadcasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģĸ
    -0.72
    ña
    -0.70
    ario
    -0.69
     princip
    -0.69
     Pwr
    -0.67
    ©¶æ¥µ
    -0.66
     Meteor
    -0.65
    ados
    -0.65
    ngth
    -0.63
    adoes
    -0.60
    POSITIVE LOGITS
    enegger
    0.79
    nesday
    0.75
     topics
    0.72
     hypot
    0.71
    pause
    0.71
    xual
    0.71
     topic
    0.70
    construct
    0.68
     forums
    0.68
    apters
    0.68
    Act Density 0.371%

    No Known Activations