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

    Neuronpedia

    INDEX
    Explanations

    names of specific places or individuals containing the sequence "je"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of names or titles in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.75
    inventory
    -0.73
    ites
    -0.72
    ayers
    -0.72
    spring
    -0.72
    norm
    -0.70
    izoph
    -0.69
    umin
    -0.68
    corn
    -0.68
    prop
    -0.68
    POSITIVE LOGITS
    anwhile
    1.10
    lde
    1.04
    ktop
    0.95
    eling
    0.89
    lda
    0.84
    uration
    0.82
    je
    0.73
    elin
    0.72
    Å¡
    0.69
    orge
    0.68
    Act Density 0.019%

    No Known Activations