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

    Neuronpedia

    INDEX
    Explanations

    verbs related to identifying or recognizing things

    oai_token-act-pair · gpt-3.5-turbo

    words related to the act of identifying or recognizing subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ework
    -0.75
    orld
    -0.74
    fare
    -0.72
     acquitted
    -0.69
    mare
    -0.67
    icum
    -0.64
     preached
    -0.64
     helicop
    -0.64
    perty
    -0.64
    oly
    -0.62
    POSITIVE LOGITS
    ively
    0.81
    ãĤ¿
    0.73
    irect
    0.72
    pointers
    0.71
     è£ıè
    0.71
    idable
    0.70
     flaws
    0.69
     Parenthood
    0.69
    acons
    0.68
     weaknesses
    0.68
    Act Density 0.036%

    No Known Activations