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

    Neuronpedia

    INDEX
    Explanations

    words related to current events or data

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "current" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jah
    -0.77
     Bei
    -0.77
    romeda
    -0.77
    wich
    -0.77
    anguage
    -0.76
    amy
    -0.72
    ppings
    -0.72
    ackle
    -0.72
    essen
    -0.71
    alty
    -0.70
    POSITIVE LOGITS
     incarnation
    0.84
     affairs
    0.78
     whereabouts
    0.75
     predicament
    0.73
    ties
    0.71
     circumstances
    0.70
     iteration
    0.67
    lly
    0.67
     occupant
    0.65
     residents
    0.64
    Act Density 0.024%

    No Known Activations