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

    Neuronpedia

    INDEX
    Explanations

    features and functions related to software utility and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eniable
    -0.15
    çµµ
    -0.15
     xung
    -0.15
     Damen
    -0.14
    iller
    -0.14
    909
    -0.14
     fractional
    -0.14
    ĺ
    -0.13
     ><?
    -0.13
    illac
    -0.13
    POSITIVE LOGITS
     Useful
    0.20
     useful
    0.17
    èŃ
    0.17
     valuable
    0.16
    ToWorld
    0.16
     usefulness
    0.16
    ermen
    0.15
    çĶ¨äºİ
    0.15
    år
    0.15
    otte
    0.15
    Act Density 0.183%

    No Known Activations