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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "catch" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amient
    -0.16
    hum
    -0.15
    antity
    -0.15
    ndern
    -0.15
    xes
    -0.14
    minent
    -0.14
    xed
    -0.14
    ÑģÑĮ
    -0.14
    quential
    -0.14
    elsing
    -0.14
    POSITIVE LOGITS
     caught
    0.17
    chas
    0.17
    ey
    0.17
    ingly
    0.16
    phrase
    0.16
    resses
    0.16
    RESS
    0.15
    ress
    0.15
     catching
    0.15
    arya
    0.15
    Act Density 0.040%

    No Known Activations