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

    Neuronpedia

    INDEX
    Explanations

    locations or objects related to physical structures

    oai_token-act-pair · gpt-3.5-turbo

    locations and settings associated with incidents or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sexes
    -0.81
    Ps
    -0.75
     positives
    -0.74
    phas
    -0.69
     Parties
    -0.66
     prizes
    -0.66
    ernels
    -0.63
     feats
    -0.63
     tokens
    -0.63
     pics
    -0.63
    POSITIVE LOGITS
     courtyard
    0.83
    robe
    0.81
     riddled
    0.79
     balcony
    0.76
     overlooking
    0.76
     blender
    0.75
     alley
    0.74
     café
    0.73
     hallway
    0.73
     airst
    0.72
    Act Density 0.373%

    No Known Activations