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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "give" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions and variations of the word "give"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sphere
    -0.68
    antha
    -0.68
    Area
    -0.60
    tenance
    -0.60
    stal
    -0.56
    ategy
    -0.56
    lander
    -0.56
    can
    -0.56
    itect
    -0.55
    âĹ¼
    -0.55
    POSITIVE LOGITS
     rise
    1.10
     birth
    1.07
     chase
    1.03
    aways
    0.91
     speeches
    0.87
     away
    0.85
     refunds
    0.82
    away
    0.82
     us
    0.81
     cred
    0.80
    Act Density 0.091%

    No Known Activations