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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences where a location or direction is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nadu
    -0.73
    Reviewer
    -0.67
    soever
    -0.67
    NING
    -0.67
     Sorceress
    -0.66
    ription
    -0.65
     Nir
    -0.65
     devised
    -0.63
    ÃŃs
    -0.60
    insula
    -0.60
    POSITIVE LOGITS
    odes
    0.79
    effic
    0.78
    ordinate
    0.76
    animate
    0.73
    pless
    0.73
    thur
    0.70
    effect
    0.69
    anz
    0.68
    roads
    0.66
     parity
    0.66
    Act Density 0.437%

    No Known Activations