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

    Neuronpedia

    INDEX
    Explanations

    opinionated posts or customer service information

    oai_token-act-pair · gemini-2.0-flash

    the word 'without'

    np_token-act-pair-logits · gpt-4o-mini

    without

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HomeAsUpEnabled
    -0.58
     protoimpl
    -0.53
    ++]=
    -0.50
    olk
    -0.49
    Parcelize
    -0.49
     <=",
    -0.47
    typeorm
    -0.47
    olsa
    -0.46
    GrantedAuthority
    -0.46
    astă
    -0.45
    POSITIVE LOGITS
     without
    3.23
     Without
    2.88
    without
    2.84
    Without
    2.83
     WITHOUT
    2.52
     zonder
    2.45
     ohne
    2.41
     tanpa
    2.34
     senza
    2.33
    WITHOUT
    2.30
    Act Density 5.854%

    No Known Activations