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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing anticipation or positive regard towards a person or event

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating anticipation or excitement for upcoming events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Intro
    -0.66
     srfAttach
    -0.66
    olla
    -0.66
    activ
    -0.60
    enter
    -0.59
     Particip
    -0.59
     ®
    -0.59
     homepage
    -0.58
     residence
    -0.57
     attm
    -0.57
    POSITIVE LOGITS
     him
    0.88
    ichick
    0.80
    ascript
    0.78
     congratulate
    0.77
     awarding
    0.76
    merce
    0.70
     pity
    0.69
     assign
    0.67
     HIM
    0.65
     admire
    0.65
    Act Density 1.077%

    No Known Activations