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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being open to doing something or accepting a certain situation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of willingness or ability to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icles
    -0.87
    icle
    -0.86
    verbs
    -0.78
    groups
    -0.76
     Surv
    -0.71
     Siber
    -0.71
     Tid
    -0.69
    DA
    -0.68
    idden
    -0.68
    inas
    -0.66
    POSITIVE LOGITS
     willingness
    1.02
     attitude
    0.87
     unwillingness
    0.86
    yip
    0.82
     adherence
    0.80
     guiActiveUn
    0.78
    ï¸
    0.78
     reluctance
    0.77
     ACTIONS
    0.75
     reliance
    0.75
    Act Density 0.032%

    No Known Activations