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

    Neuronpedia

    INDEX
    Explanations

    time-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of ongoing discussions or commentary surrounding controversial topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oha
    -0.59
    opter
    -0.59
    Fuck
    -0.57
    ãħĭãħĭ
    -0.57
    ĸ
    -0.56
    romy
    -0.56
    HO
    -0.56
    oir
    -0.54
    FK
    -0.54
    oples
    -0.54
    POSITIVE LOGITS
    edia
    0.72
     inevitably
    0.71
    pmwiki
    0.69
     tensions
    0.68
     increasingly
    0.65
    Incre
    0.65
     Collider
    0.64
     escalating
    0.62
     increasing
    0.61
    BLIC
    0.61
    Act Density 0.269%

    No Known Activations