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

    Neuronpedia

    INDEX
    Explanations

    references to motivation and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ialog
    -0.17
     Battle
    -0.16
    hole
    -0.16
    holes
    -0.15
    ftime
    -0.15
    Battle
    -0.15
    ister
    -0.15
    icken
    -0.14
    editable
    -0.14
    vez
    -0.14
    POSITIVE LOGITS
    ivated
    0.27
    ivation
    0.25
    oring
    0.23
    amedi
    0.22
    ivating
    0.21
    swana
    0.20
    gomery
    0.19
    ives
    0.19
    tingham
    0.19
    mot
    0.18
    Act Density 0.008%

    No Known Activations