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

    Neuronpedia

    INDEX
    Explanations

    information related to job roles and responsibilities

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

    Follows pronouns (we, she, some)

    np_acts-logits-general · gemini-2.0-flash

    saving or stealing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.91
     AppColors
    -0.89
     contextLoads
    -0.88
     ་་
    -0.85
     Theſe
    -0.81
     doubtnut
    -0.81
     Efq
    -0.77
     thereof
    -0.76
     favourably
    -0.76
     ―――――
    -0.76
    POSITIVE LOGITS
     compare
    0.72
     confuse
    0.64
     alway
    0.64
     limitation
    0.62
     Sometime
    0.62
     Beside
    0.62
     create
    0.61
     saja
    0.60
     combine
    0.57
     condition
    0.57
    Act Density 0.183%

    No Known Activations