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

    Neuronpedia

    INDEX
    Explanations

    words related to a playing surface or a place

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical settings, resources, and spatial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.79
    ritch
    -0.75
    ciating
    -0.74
    ²¾
    -0.73
    Ô
    -0.72
    rez
    -0.72
    gemony
    -0.70
    umn
    -0.70
    ãĥį
    -0.69
    umenthal
    -0.69
    POSITIVE LOGITS
     optimization
    0.69
     iP
    0.62
     Axe
    0.61
     plank
    0.59
    imus
    0.59
     pedest
    0.56
     pamph
    0.56
     Tuls
    0.55
     Gauntlet
    0.55
    eers
    0.55
    Act Density 0.328%

    No Known Activations