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

    Neuronpedia

    INDEX
    Explanations

    verbs related to movement or progression

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating movement or progression through space or time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¡
    -0.74
    ª
    -0.74
    EMENT
    -0.74
    £
    -0.72
    ²¾
    -0.67
    Default
    -0.66
    Ĵ
    -0.65
    ÙIJ
    -0.63
    facing
    -0.63
    TE
    -0.62
    POSITIVE LOGITS
     obscurity
    0.84
    wards
    0.83
    Downloadha
    0.82
     hither
    0.81
     corners
    0.74
     bushes
    0.74
     Stam
    0.73
     onto
    0.73
    nir
    0.72
     unnoticed
    0.67
    Act Density 0.308%

    No Known Activations