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

    Neuronpedia

    INDEX
    Explanations

    instances where something is being missed out on

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating missing opportunities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ku
    -0.59
    Äĩ
    -0.55
     Primordial
    -0.54
     hips
    -0.53
     blade
    -0.53
    IOR
    -0.53
     withdrawn
    -0.53
     retri
    -0.53
    raltar
    -0.52
     Dak
    -0.52
    POSITIVE LOGITS
    stretched
    0.85
    ertodd
    0.83
    doors
    0.81
    casts
    0.76
    heses
    0.72
    alks
    0.69
    paces
    0.69
    ners
    0.67
    fitted
    0.66
    ricular
    0.65
    Act Density 0.052%

    No Known Activations