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

    Neuronpedia

    INDEX
    Explanations

    words related to the vertical direction or orientation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "vertical" concepts or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    giving
    -0.97
    keeper
    -0.89
    keeping
    -0.88
    keepers
    -0.78
    ãģ®éŃĶ
    -0.77
    taking
    -0.76
    bane
    -0.75
    urai
    -0.75
    ãģ¦
    -0.75
    ptives
    -0.74
    POSITIVE LOGITS
     axis
    1.05
     dimension
    1.00
     vertical
    0.96
     dimensions
    0.93
     separation
    0.89
     ascent
    0.89
     shaft
    0.88
     horizontal
    0.88
     stripes
    0.87
     takeoff
    0.85
    Act Density 0.018%

    No Known Activations