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

    Neuronpedia

    INDEX
    Explanations

    locations or positions described using prepositions

    oai_token-act-pair · gpt-3.5-turbo

    instances of sitting or being in physical proximity to specific locations or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ().
    -0.76
    Ĥİ
    -0.72
    ERO
    -0.70
    EMA
    -0.70
    Ī
    -0.70
     Flavoring
    -0.69
    Course
    -0.68
    ²¾
    -0.68
    ERG
    -0.66
    lance
    -0.65
    POSITIVE LOGITS
     pedest
    0.86
     doorway
    0.82
     throne
    0.80
     benches
    0.80
     darkened
    0.79
     couch
    0.78
     porch
    0.77
     sofa
    0.77
     podium
    0.76
     bushes
    0.75
    Act Density 0.321%

    No Known Activations