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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to uncertainty or hesitation

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to uncertainty and cautiousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    region
    -0.80
    è£ħ
    -0.78
    Reviewer
    -0.77
    abad
    -0.74
    onne
    -0.74
    ridges
    -0.74
    DoS
    -0.74
    ulhu
    -0.72
    alach
    -0.71
    FactoryReloaded
    -0.70
    POSITIVE LOGITS
     tentative
    1.02
     ceasefire
    0.80
     equilibrium
    0.79
     easing
    0.76
     peg
    0.75
     bargaining
    0.75
     alliance
    0.75
     truce
    0.70
     hesitation
    0.69
     flirt
    0.69
    Act Density 0.007%

    No Known Activations