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

    Neuronpedia

    INDEX
    Explanations

    words related to significant changes or transitions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "transform" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PLIED
    -0.68
    ramid
    -0.67
    REL
    -0.66
     LIMITED
    -0.63
    cheat
    -0.62
    ourn
    -0.61
    zzi
    -0.61
    xia
    -0.61
    epad
    -0.60
     WARN
    -0.60
    POSITIVE LOGITS
    ively
    0.83
    atile
    0.82
     transforms
    0.82
    ational
    0.80
     transform
    0.80
    ives
    0.80
     transformations
    0.76
     transformation
    0.74
    into
    0.73
    ãĥĥ
    0.73
    Act Density 0.035%

    No Known Activations