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

    Neuronpedia

    INDEX
    Explanations

    statements of opinion and speculation

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

    "I think" constructions

    np_acts-logits-general · gemini-2.0-flash

    i think that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.99
     Efq
    -0.97
    ſelves
    -0.91
    ſelf
    -0.91
     ―――――
    -0.88
     himſelf
    -0.87
    PerformLayout
    -0.87
    脚注の使い方
    -0.86
     autorytatywna
    -0.85
     houſe
    -0.84
    POSITIVE LOGITS
     it
    0.84
     we
    0.82
     there
    0.74
     they
    0.69
     that
    0.69
     if
    0.66
     you
    0.65
     this
    0.60
     the
    0.56
    ,
    0.54
    Act Density 0.259%

    No Known Activations