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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "wave"

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of "waves" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orate
    -0.78
    atem
    -0.73
    heid
    -0.73
    azeera
    -0.72
    rontal
    -0.71
    mingham
    -0.70
    ioch
    -0.70
    ancies
    -0.68
    uracy
    -0.65
    oses
    -0.64
    POSITIVE LOGITS
    guide
    1.03
    wave
    0.90
     wave
    0.90
    form
    0.89
    front
    0.85
    rers
    0.82
    forms
    0.81
    tro
    0.80
    boat
    0.79
    stakes
    0.79
    Act Density 0.020%

    No Known Activations