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

    Neuronpedia

    INDEX
    Explanations

    equal signs in code or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InitStruct
    -0.70
     Hoy
    -0.63
     Ș
    -0.62
    ness
    -0.61
     socc
    -0.60
    ound
    -0.59
    Hoy
    -0.58
    lli
    -0.57
     Heff
    -0.57
    neſs
    -0.57
    POSITIVE LOGITS
     =
    1.81
    /=
    1.71
    >=</
    1.69
    )=
    1.33
    }=
    1.31
     $=
    1.30
     $=\
    1.28
    ]=
    1.26
     $=$
    1.25
    _=
    1.24
    Act Density 0.259%

    No Known Activations