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

    Neuronpedia

    INDEX
    Explanations

    words related to attracting or enticing someone

    oai_token-act-pair · gpt-3.5-turbo

    terms related to luring or enticing individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PRESIDENT
    -0.69
    stood
    -0.68
    acterial
    -0.67
    arrow
    -0.66
    iop
    -0.66
    undred
    -0.66
    arna
    -0.66
    actions
    -0.64
    oret
    -0.63
    aration
    -0.63
    POSITIVE LOGITS
     lure
    1.32
     lured
    1.06
    GGGGGGGG
    0.89
     prey
    0.84
     bait
    0.78
    xtap
    0.75
     unsuspecting
    0.71
    glers
    0.71
     tempt
    0.71
    EStream
    0.70
    Act Density 0.010%

    No Known Activations