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

    Neuronpedia

    INDEX
    Explanations

    emotional states and social interactions related to self-awareness and longing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¤Ĥà¤ľà¤¨
    -0.16
    ffee
    -0.15
    лÑıн
    -0.15
    rompt
    -0.15
    eor
    -0.14
    رز
    -0.14
    uest
    -0.14
    itti
    -0.14
    容
    -0.14
    ìĬ¤ì½Ķ
    -0.13
    POSITIVE LOGITS
     instead
    0.27
     Instead
    0.25
    Instead
    0.23
    instead
    0.23
     sed
    0.17
    isd
    0.15
     ãĥĢ
    0.15
     elsewhere
    0.14
     вмеÑģÑĤ
    0.14
    atched
    0.14
    Act Density 0.117%

    No Known Activations