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

    Neuronpedia

    INDEX
    Explanations

    terms related to user-friendliness and accessibility features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     résult
    -0.53
     ricevuto
    -0.49
     lccn
    -0.48
    ahan
    -0.48
     Persön
    -0.47
     عقد
    -0.47
     valueForKey
    -0.46
    ARROLL
    -0.46
     vinto
    -0.46
    Varint
    -0.45
    POSITIVE LOGITS
     friendly
    1.98
    friendly
    1.71
     Friendly
    1.64
    Friendly
    1.57
     compatible
    1.38
     friendliness
    1.34
     FRIEND
    1.32
     unfriendly
    1.22
     compliant
    1.19
    FRIEND
    1.16
    Act Density 0.355%

    No Known Activations