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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating a direction or movement towards something

    oai_token-act-pair · gpt-3.5-turbo

    directional terms indicating movement or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     briefed
    -0.70
    drivers
    -0.70
     pitted
    -0.69
    umm
    -0.68
    named
    -0.67
    UL
    -0.67
    codes
    -0.65
    cu
    -0.65
    pots
    -0.65
    cats
    -0.63
    POSITIVE LOGITS
     toward
    0.90
    vernment
    0.82
    WARD
    0.81
    ward
    0.81
     towards
    0.80
    wards
    0.80
    ments
    0.78
     infinity
    0.77
     Towards
    0.76
     adulthood
    0.70
    Act Density 0.031%

    No Known Activations