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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a change in direction or situation

    oai_token-act-pair · gpt-3.5-turbo

    references to changes or transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tumblr
    -0.74
    è¦ļéĨĴ
    -0.72
    MER
    -0.72
    POST
    -0.69
    enegger
    -0.69
    anwhile
    -0.68
    PLIED
    -0.67
    aturdays
    -0.63
    cliffe
    -0.63
    ertation
    -0.63
    POSITIVE LOGITS
    oward
    0.81
     knob
    0.78
     lifeless
    0.75
     INTO
    0.71
     fortunes
    0.70
     inward
    0.69
     into
    0.68
     Into
    0.68
    ¦
    0.66
     Away
    0.65
    Act Density 0.106%

    No Known Activations