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

    Neuronpedia

    INDEX
    Explanations

    the word "almost" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierge
    -0.18
    aro
    -0.16
    ponge
    -0.16
    edic
    -0.15
    adam
    -0.15
    illisecond
    -0.15
    iná
    -0.15
    idd
    -0.15
    iêu
    -0.14
    еÑĢап
    -0.14
    POSITIVE LOGITS
    afia
    0.17
    SystemService
    0.16
    lian
    0.16
    oire
    0.15
     disap
    0.15
    eced
    0.15
     Fat
    0.15
    thood
    0.14
     bon
    0.14
    itious
    0.14
    Act Density 0.024%

    No Known Activations