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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to vertical orientation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vertical and horizontal structures or arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.86
    giving
    -0.84
    ãģ®éŃĶ
    -0.84
    nil
    -0.80
    mberg
    -0.79
    IVERS
    -0.77
    keeper
    -0.76
    ãģ¦
    -0.76
    unes
    -0.75
    lyak
    -0.75
    POSITIVE LOGITS
     axis
    1.08
     dimension
    0.93
     stabil
    0.92
     takeoff
    0.90
     separation
    0.89
     stripes
    0.87
     leap
    0.87
     ascent
    0.87
     dashed
    0.86
     plane
    0.85
    Act Density 0.024%

    No Known Activations