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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interrupted
    -0.85
    ymes
    -0.66
    apse
    -0.65
     unemploy
    -0.64
     ens
    -0.64
     sacked
    -0.63
     impossibility
    -0.62
     brim
    -0.62
    aked
    -0.62
    URA
    -0.61
    POSITIVE LOGITS
    roads
    0.92
     regards
    0.92
    versions
    0.81
     regard
    0.80
    clusions
    0.76
    utm
    0.76
    eff
    0.75
    efficiency
    0.71
     tandem
    0.71
    humane
    0.69
    Act Density 0.248%

    No Known Activations