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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their surrounding phrases or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.56
    sph
    -0.51
    oredCriteria
    -0.50
    SourceChecksum
    -0.50
     JAM
    -0.47
    adaptiveStyles
    -0.47
    CPtr
    -0.46
     Vale
    -0.46
    Autoritní
    -0.45
    InvalidProtocol
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.56
     sebaliknya
    0.50
     enfance
    0.50
     andererseits
    0.49
     poème
    0.47
     alternatively
    0.47
    httphttps
    0.47
     amitié
    0.46
     oppure
    0.46
    étranger
    0.45
    Act Density 0.588%

    No Known Activations