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

    Neuronpedia

    INDEX
    Explanations

    references to the location "Kyiv" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Ky" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ional
    -0.86
     à¨
    -0.78
    heads
    -0.77
    ACTED
    -0.75
    ential
    -0.74
    IBLE
    -0.71
    ãĥĩãĤ£
    -0.69
    perture
    -0.67
    head
    -0.66
    bidden
    -0.65
    POSITIVE LOGITS
    Ky
    0.95
    nect
    0.84
    ush
    0.83
    annis
    0.83
    olk
    0.83
    kees
    0.83
    orea
    0.82
    ewitness
    0.82
    oko
    0.80
    oshi
    0.79
    Act Density 0.010%

    No Known Activations