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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating clarity or proof of expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zl
    -0.17
    isses
    -0.16
    owitz
    -0.15
    νÏİ
    -0.14
    addock
    -0.14
    оÑĢÑĤÑĥ
    -0.14
    ?url
    -0.14
    ãĥ³ãĥĪ
    -0.14
    _BORDER
    -0.14
    zzle
    -0.13
    POSITIVE LOGITS
     wonder
    0.61
     Wonder
    0.45
     wondered
    0.36
     wonders
    0.35
    Wonder
    0.35
     wondering
    0.31
     unsur
    0.27
    onder
    0.27
     surprise
    0.26
    sur
    0.25
    Act Density 0.118%

    No Known Activations