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

    Neuronpedia

    INDEX
    Explanations

    words related to spatial directions or positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to directionality and measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elta
    -0.77
    akia
    -0.66
    ãĤĵ
    -0.64
    ongo
    -0.64
    ̶
    -0.62
    onis
    -0.61
    ificant
    -0.61
    paio
    -0.60
    arna
    -0.59
    orously
    -0.58
    POSITIVE LOGITS
     specified
    0.94
     of
    0.89
     outlined
    0.89
     described
    0.84
     mentioned
    0.83
     thereof
    0.79
     indicated
    0.78
     depicted
    0.76
     envisioned
    0.76
     prescribed
    0.76
    Act Density 0.172%

    No Known Activations