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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal reactions and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flem
    -0.16
    ALSE
    -0.16
    оÑĢож
    -0.15
    regor
    -0.15
    avra
    -0.15
    ål
    -0.15
    amespace
    -0.15
    eyin
    -0.15
    MOTE
    -0.15
    emez
    -0.15
    POSITIVE LOGITS
     aware
    0.23
     feel
    0.23
     proud
    0.21
     gig
    0.20
     uncomfortable
    0.20
     happy
    0.20
     into
    0.20
     fall
    0.20
     comfortable
    0.20
     sad
    0.19
    Act Density 0.036%

    No Known Activations