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

    Neuronpedia

    INDEX
    Explanations

    phrases related to bringing or introducing something new or significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odor
    -0.15
     dobÅĻe
    -0.14
    ern
    -0.14
    .setTime
    -0.14
    opp
    -0.13
    ampus
    -0.13
    ARB
    -0.13
    iron
    -0.13
    iro
    -0.13
    can
    -0.13
    POSITIVE LOGITS
    ToFront
    0.20
    ÄĽst
    0.16
    899
    0.16
    endum
    0.16
     forth
    0.16
    uluk
    0.15
    inh
    0.15
    elly
    0.14
    ODB
    0.14
    izmet
    0.14
    Act Density 0.048%

    No Known Activations