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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "only" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    only followed by quantifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     byg
    -0.47
     FISCAL
    -0.45
     avulla
    -0.45
     vôtre
    -0.45
    Identi
    -0.45
    RTCF
    -0.44
     identité
    -0.44
    IsPostBack
    -0.44
    Спољашње
    -0.44
     miejsce
    -0.44
    POSITIVE LOGITS
     been
    0.50
     ever
    0.49
    ParallelGroup
    0.47
     EVER
    0.45
    IUrlHelper
    0.45
    有过
    0.43
     recently
    0.42
    ErrUnexpectedEOF
    0.42
    jména
    0.42
     heretofore
    0.42
    Act Density 0.005%

    No Known Activations