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

    Neuronpedia

    INDEX
    Explanations

    concepts related to seeking or providing help and assistance in various situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to support and assistance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mile
    -0.58
    bey
    -0.56
     outing
    -0.55
     nature
    -0.54
    ovie
    -0.54
     Lonely
    -0.53
     tallied
    -0.51
     Nichols
    -0.51
     blur
    -0.50
     relent
    -0.50
    POSITIVE LOGITS
    aram
    0.75
    iless
    0.67
    fully
    0.67
    âĨij
    0.66
     abroad
    0.64
    java
    0.63
    DragonMagazine
    0.63
    matically
    0.61
    Credits
    0.61
    tips
    0.60
    Act Density 0.372%

    No Known Activations