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

    Neuronpedia

    INDEX
    Explanations

    phrases related to alignment or balance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jsonResponse
    -0.16
    ic
    -0.15
    oshi
    -0.15
    Ñģи
    -0.15
    icari
    -0.14
    strict
    -0.14
    unu
    -0.14
    icina
    -0.14
    ties
    -0.14
    ated
    -0.14
    POSITIVE LOGITS
    ingly
    0.21
    -match
    0.20
    able
    0.18
    (es
    0.18
    -up
    0.17
    (match
    0.17
    ering
    0.16
    DispatchToProps
    0.16
     match
    0.16
    up
    0.16
    Act Density 0.058%

    No Known Activations