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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to attracting attention or interest

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with attraction or drawing interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utral
    -0.73
    phrine
    -0.71
    unker
    -0.68
    hal
    -0.66
    pine
    -0.66
    eden
    -0.65
    ocker
    -0.65
     FSA
    -0.64
    orah
    -0.62
    chen
    -0.62
    POSITIVE LOGITS
     attract
    1.13
     attracts
    1.11
     attracting
    0.90
    GGGGGGGG
    0.85
     attractions
    0.84
     promot
    0.82
     lure
    0.81
     attractive
    0.81
     attracted
    0.80
    entious
    0.77
    Act Density 0.009%

    No Known Activations