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

    Neuronpedia

    INDEX
    Explanations

    keywords related to capturing or taking hold of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "capture" and its forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amen
    -0.71
    pace
    -0.70
    ple
    -0.69
    jab
    -0.68
     mascul
    -0.67
    bye
    -0.65
    arten
    -0.65
     inclined
    -0.64
     conflic
    -0.63
    endix
    -0.63
    POSITIVE LOGITS
    racuse
    0.86
    Capt
    0.76
     Thumbnails
    0.76
     captured
    0.74
    vich
    0.71
    alogue
    0.70
    doors
    0.67
    oufl
    0.67
    ively
    0.67
    és
    0.66
    Act Density 0.026%

    No Known Activations