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

    Neuronpedia

    INDEX
    Explanations

    mentions related to conflicts of interest in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "L" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disadvant
    -0.77
     vulner
    -0.70
     bed
    -0.65
     decap
    -0.63
     fortun
    -0.63
     mathemat
    -0.61
     optimizations
    -0.61
     fodder
    -0.60
    ickets
    -0.60
     gib
    -0.60
    POSITIVE LOGITS
    ï¸ı
    1.07
    ï¸
    0.89
    own
    0.81
    lime
    0.80
    shall
    0.76
    felt
    0.75
    sure
    0.73
    ski
    0.69
    reci
    0.68
    ti
    0.68
    Act Density 0.285%

    No Known Activations