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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intentions or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iani
    -0.15
    pat
    -0.15
     Fortune
    -0.14
    erap
    -0.14
    imir
    -0.14
    hw
    -0.14
    erial
    -0.14
    _avail
    -0.13
    arrants
    -0.13
    erve
    -0.13
    POSITIVE LOGITS
    ascript
    0.16
    ÙĦÙĤ
    0.16
    ĵåIJį
    0.15
    ROUGH
    0.15
     IonicPage
    0.15
    XObject
    0.15
    enet
    0.15
    rig
    0.15
    nnen
    0.14
    quam
    0.14
    Act Density 0.144%

    No Known Activations