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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific locations or events

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical locations and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.84
    oulos
    -0.83
    ocate
    -0.82
    encers
    -0.81
    ngth
    -0.80
    haar
    -0.79
    escription
    -0.77
    ritis
    -0.76
    auts
    -0.75
    blers
    -0.74
    POSITIVE LOGITS
     occasions
    1.26
     basis
    1.15
     behalf
    1.01
     footing
    0.92
     occasion
    0.90
     grounds
    0.88
     pretext
    0.87
     fronts
    0.85
     doorstep
    0.83
     eve
    0.81
    Act Density 0.919%

    No Known Activations