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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating action or movement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "went"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullah
    -0.71
     ---------
    -0.67
    icio
    -0.65
    eers
    -0.65
    psey
    -0.62
    utters
    -0.61
    oret
    -0.60
    cape
    -0.60
    course
    -0.59
    ipation
    -0.59
    POSITIVE LOGITS
     overboard
    1.02
    verning
    0.99
    ©¶æ
    0.91
    vt
    0.84
    lems
    0.83
     forth
    0.83
    ggle
    0.81
    ħĭ
    0.80
     bankrupt
    0.80
     forward
    0.78
    Act Density 0.102%

    No Known Activations