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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to fear or causing fear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    scare and frighten

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IndexPath
    -0.40
    Remain
    -0.39
    つの
    -0.38
    ️
    -0.38
    RequestOptions
    -0.38
     Pion
    -0.37
    ItemIndex
    -0.37
     MDC
    -0.37
     CFP
    -0.36
     NDP
    -0.36
    POSITIVE LOGITS
     scare
    1.63
     scares
    1.32
     scaring
    1.27
     frighten
    1.05
     fright
    0.86
    scared
    0.81
     effray
    0.80
    Scared
    0.79
     scared
    0.79
     asust
    0.74
    Act Density 0.005%

    No Known Activations