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

    Neuronpedia

    INDEX
    Explanations

    terms associated with targeting and goals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dear
    -0.16
    IGH
    -0.16
    quer
    -0.15
    ibur
    -0.15
    bons
    -0.15
    ances
    -0.14
    enia
    -0.14
    amina
    -0.14
    raj
    -0.14
    erty
    -0.14
    POSITIVE LOGITS
    ted
    0.31
    ting
    0.24
    ="_
    0.23
    (Target
    0.20
    /target
    0.18
    =target
    0.18
    Touches
    0.18
    edReader
    0.17
    entin
    0.17
    tır
    0.17
    Act Density 0.031%

    No Known Activations