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

    Neuronpedia

    INDEX
    Explanations

    words related to personal achievements or attributes, such as skills, conditions, or qualities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to struggles and challenges faced by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.61
     oneself
    -0.55
    uador
    -0.55
     extrad
    -0.52
     Guan
    -0.51
     Salv
    -0.50
     Majority
    -0.49
     Cald
    -0.48
     yourselves
    -0.48
    ÅŁ
    -0.48
    POSITIVE LOGITS
     counterparts
    0.97
     counterpart
    0.82
     brethren
    0.79
     selves
    0.77
     buddies
    0.75
     mates
    0.73
     arsenal
    0.69
    mates
    0.69
     cousins
    0.69
     cousin
    0.67
    Act Density 0.810%

    No Known Activations