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

    Neuronpedia

    INDEX
    Explanations

    adjectives or verbs related to negative or unfortunate situations

    oai_token-act-pair · gpt-3.5-turbo

    prefixes or stems that suggest negativity or misfortune

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.76
     Barker
    -0.66
     Lambert
    -0.66
     Christy
    -0.62
     VIDEOS
    -0.61
    Developer
    -0.61
    tti
    -0.59
     GAM
    -0.59
    Bank
    -0.57
    minster
    -0.57
    POSITIVE LOGITS
    akable
    1.16
    oppable
    1.08
    cedented
    1.05
    ailability
    0.93
    ailable
    0.86
    ables
    0.85
    quished
    0.85
    ernel
    0.84
    ached
    0.82
    ench
    0.82
    Act Density 0.066%

    No Known Activations