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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "All this" where something significant or important is described

    oai_token-act-pair · gpt-3.5-turbo

    repetitive references to "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sword
    -0.76
    oru
    -0.75
    aws
    -0.73
     Tracks
    -0.72
    »Ĵ
    -0.72
    ARB
    -0.63
    omew
    -0.62
    Ħ
    -0.61
    Soul
    -0.60
    ics
    -0.60
    POSITIVE LOGITS
     happened
    0.85
     culminated
    0.83
     happening
    0.82
     happens
    0.82
     madness
    0.81
    together
    0.79
    worldly
    0.78
     ado
    0.77
     happen
    0.76
     transpired
    0.76
    Act Density 0.038%

    No Known Activations